检索结果-内蒙古大学图书馆

1st International Conference on Innovations in Communications, Electrical and computer engineering, ICICEC 2024

作者： Swetha, P. Sreenivasa, B.R. Pes University Department of Computer Science and Engineering Bangalore India Bapuji Institute of Engineering & Technology Department of Computer Science and Design Davangere India

ISBN: (数字)9798350376517

ISBN: (纸本)9798350376517

Understanding and interpreting sign languages are crucial for promoting communication among the Deaf and Hard of Hearing (DHH) populations [1]. Kannada Sign Language (KSL), primarily utilized in Karnataka, lacks sufficient digital tools and technical support compared to several other well-studied sign languages. To reduce this gap, this study uses machine language learning (ML) techniques to convert KSL gestures into text and speech. The hand movements and facial expressions used in the KSL signs were gathered and examined for this purpose. Convolutional neural networks (CNNs) and recurrent neural networks (RNNs), two examples of advanced machine-learning methods, have been used to create a reliable recognition system that can perform KSL in real time. The model has shown promising accuracy rates in the preliminary findings, instilling confidence in its potential to enhance KSL users' communication significantly. This study aims to improve education and daily communication among KSL speakers. The proposed model can be used at the regional Primary Healthcare Centers (PHC) for the effective interaction of a patient and doctors. In the future, we plan to expand the dataset, improve the algorithmic performance, and create user-friendly programs to make such programs useful at urban hospitals, too. © 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

An intrusion detection system based on hybrid machine learning classifier

引用

Journal of Intelligent and Fuzzy Systems 2023年第3期44卷 4245-4255页

作者： Reji, M. Joseph, Christeena Nancy, P. Lourdes Mary, A. Department of Electronics and Communication Engineering Rohini College of Engineering and Technology Tamilnadu Kanyakumari India Department of Electronics and Communication Engineering Srm Institute of Science and Technology Tamilnadu Chennai India Department of Computing Technologies School of Computing Srm Institute of Science and Technology Kattankulathur Campus Chennai India Department of Computer Science and Engineering Rohini College of Engineering and Technology Tamilnadu Kanyakumari India

Intrusion detection systems (IDS) can be used to detect irregularities in network traffic to improve network security and protect data and systems. From 2.4 times in 2018 to three times in 2023, the number of devices linked to IP networks is predicted to outnumber the total population of the world. In 2020, approximately 1.5 billion cyber-attacks on Internet of Things (IoT) devices have been reported. Classification of these attacks in the IoT network is the major objective of this research. This research proposes a hybrid machine learning model using Seagull Optimization Algorithm (SOA) and Extreme Learning Machine (ELM) classifier to classify and detect attacks in IoT networks. The CIC-IDS-2018 dataset is used in this work to evaluate the proposed model. The SOA is implemented for feature selection from the dataset, and the ELM is used to classify attacks from the selected features. The dataset has 80 features, in the proposed model used only 22 features with higher scores than the original dataset. The dataset is divided into 80% for training and 20% for testing. The proposed SOA-ELM model obtained 94.22% accuracy, 92.95% precision, 93.45% detection rate, and 91.26% f1-score. © 2022 - IOS Press. All rights reserved.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Enhanced Agricultural Decision-Making: Merging Climatic Data with Machine Learning Algorithms 5

Enhanced Agricultural Decision-Making: Merging Climatic Data...

引用

5th International Conference on Data Intelligence and Cognitive Informatics, ICDICI 2024

作者： Rathi, Snehal Wamanacharya, Shubham Shah, Samkit Khedkar, Vijayshri BTACT'S Vishwakarma Institute of Information Technology Department of Computer Engineering Pune India Symbiosis Institute of Technology Department of Computer Science & Engineering Pune India

ISBN: (纸本)9798350389609

Climate change still implies risks for economic security, such as for agriculture and its productivity and, therefore, national economic potential. Although similar approaches have been used in publications concerning individual crops or soil types, the application of climatology parameters in agriculture and it limited indices have not been optimal. Owing to the recognized limitations of traditional linear productivity models, this thesis subjects' agricultural productivity to a Cobb-Douglas multi-factorial modeling approach through intensive levels of data decomposition. The proposed approach enabled the researchers to adjust the impact of climate parameters during students' evaluations in the secondary education curricula. Additionally, frameworks which relate temperature variations and crop growth do exist, and therefore the temperature and agriculture performance model effects determinants were determined using complex analysis of temperature relations and crop outputs. This highlights the various factors affecting production, its structure, and the relative importance of some conditions in agriculture and explains their dynamics depending on the changes in growth factors. Hence, a set of factors employed in the modeling resulted mainly from economic conditions, production system structures and advanced agricultural technology applications in the economy as prediction © 2024 IEEE.

关键词： Agricultural Data Analysis Climate Impact on Agriculture Crop Growth Days Growth Degree Days (GDD) R Programming

来源：评论

学校读者我要写书评

暂无评论

Deep convolutional spiking neural network fostered automatic detection and classification of breast cancer from mammography images

引用

Research on Biomedical engineering 2023年第4期39卷 833-841页

作者： SenthilPrakash, T. Kannan, G. Prabhakaran, Salini Prajapati, Bhagirath Parshuram Department of Computer Science and Engineering Shree Venkateshwara Hi-Tech Engineering College Tamil Nadu Gobichettipalayam India Department of Electronics and Communication Engineering Amrita College of Engineering and Technology Nagercoil India Department of Computer Science and Engineering Puducherry Technological University Puducherry India Department of Computer Engineering A. D. Patel Institute of Technology Gujarat New Vallabh Vidyanagar India

Purpose: Breast cancer (BC) is a leading cause of death among women. Several existing methods on breast cancer classification were suggested with machine learning, but none of them accurately classify the breast cancer and requires high computational time. To overcome these problems, deep convolutional spiking neural network fostered automatic detection and classification of breast cancer from mammography images (DCSNN-BCDC-MI) is proposed in this manuscript. Methods: Initially, input breast mammography pictures are taken from Digital Database for Screening Mammography (DDSM) data set. The input breast mammography images are pre-processed and feature extracted. The DCSNN is employed to categorize pictures using retrieved characteristics, such as benign and malignant. Results: The proposed DCSNN-BCDC-MI technique is implemented at PYTHON. The performance of the proposed DCSNN-BCDC-MI technique attains 31.13%, 12.78%, 14.38%, 19.33%, and 19.11% high accuracy and 61.08%, 66.42%, 66.54%, 50.26%, and 53.03% low computation time comparing to the existing techniques, like deep learning fed capsule neural network for breast cancer detection utilizing mammogram images (OMLTS-DLCN-BCDC-MI), extended model for tumor location detection based on deep learning (VGG-CNN-BCDC-MI), deep learning algorithm for automated identification with breast cancer classification depending on transfer-learning strategy (VGG16-BCDC-MI), deep learning method for breast cancer identification on mammography by learning certain cancerous mass representations (CNN-Deep AE-BCDC-MI), and automatic identification with mammograms classification dependent on increased extreme learning machine along deep learning (ICS-ELM-BCDC-MI), respectively. Conclusion: The simulation result exemplifies that the proposed method can be capable to determine the optimum global solutions efficiently with the exact existing methods. © 2023, The Author(s), under exclusive licence to The Brazilian Society of Biomedical Enginee

关键词： Mammography

来源：评论

学校读者我要写书评

暂无评论

Unveiling Hidden Water Resources: Deep Learning and Remote Sensing for Subsurface Hydrology for Environmental Health

引用

Remote Sensing in Earth Systems sciences 2025年第2期8卷 352-364页

作者： Babu, Jampani Satish G, Dinesh Suganya, R. Radhakrishnan, P. Sutar, Anand S, Alex David Rao, L. Malleswara Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Guntur AP Vaddeswaram India Department of Computational Intelligence School of Computing SRM Institute of Science and Technology Kattankulathur (KTR) Chennai India Department of Computer Science and Engineering (Data Science) New Horizon College of Engineering Karnataka Bengaluru India Department of ECE Tagore Engineering College Chennai India Department of Electronics and Telecommunication Bharati Vidyapeeth College of Engineering Navi Mumbai India Department of Computer Science and Engineering Vel Tech Rangarajan Dr Sagunthala R & d Institute of Science and Technology Chennai India Department of Physics Sri Y N College (A) West Godavari District Andhra Pradesh Narsapur India

Water scarcity in arid regions necessitates innovative solutions to uncover and manage subsurface water resources for environmental health. This study explores the potential of GeoHydroNet, a specialized deep learning framework, in identifying hidden water resources within arid regions. Utilizing remote sensing data such as multispectral and hyperspectral imagery, geological maps, and soil moisture datasets, GeoHydroNet combines graph neural Networks (GNNs), AutoEncoders, and generative adversarial networks (GANs) to address challenges in subsurface hydrology. The model achieved an accuracy of 93.5%, surpassing traditional models like CNNs (85.4%), LSTMs (88.1%), and RNNs (82.6%). GeoHydroNet demonstrates significant precision (0.88), recall (0.87), and sensitivity to data imbalance (0.91). Its physics-informed learning approach incorporates hydrological principles, ensuring realistic predictions. By analyzing subsurface water patterns, recharge zones, and geological influences, the model not only enhances prediction accuracy but also aids in sustainable groundwater management. GeoHydroNet’s performance in identifying groundwater levels, with minimal errors ranging from 0.62 to 3.07%, indicates its robustness in tackling water scarcity challenges in data-constrained environments. These findings highlight its transformative role in hydrological modeling and sustainable water resource management in arid regions. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.

关键词： Aquifers Arid regions Deep learning Generative adversarial networks GeoHydroNet Physics-informed learning Remote sensing Subsurface hydrology Sustainable water management

来源：评论

学校读者我要写书评

暂无评论

Automated Detection of Infection in Diabetic Foot Ulcer Using Pre-trained Fast Convolutional Neural Network with U++net

引用

SN computer science 2024年第6期5卷 1-15页

作者： Murthy, S.V.N. Bhargavi, Kovvuri N. Isaac, Samson N.Ganesh, E. Department of Computer Science and Engineering SJC Institute of Technology Information Technology Aditya College of Engineering and Technology Biomedical Engineering Karunya Institute of Technology and Sciences Department of ECE St. Peter’s Institute of Higher Education and Research

A frequent consequence of diabetes and a significant contributor to morbidity and mortality is diabetic foot ulcer (DFU).Early detection and appropriate management of DFUs are essential to prevent complications such as infections and lower extremity amputations. In recent years, medical imaging and machine learning have emerged as promising tools for the automated detection and analysis of DFUs. We gathered a sizable foot imaging dataset, including DFU from multiple patients. This paper proposes a novel preprocessing technique based on the Shades of Gray color constancy algorithm to cope with noise and lighting variations in diabetic foot ulcer (DFU) images captured from different devices. The algorithm aims to enhance image quality, improve illumination normalization, and mitigate the impact of noise, thus providing more reliable and accurate DFU analysis and detection. Using the Diabetic Foot Infection Network with the Adam Optimizer (DFINET-AO), features were retrieved after the dataset had been preprocessed and divided. In order to comprehend the normal and pathological spectrum of diabetes, image data and numerical/text data are separated independently. Foot images of patients with aberrant diabetes coverage are separated from each other and classified using Pre-trained Fast Convolutional Neural Network (PFCNN), which has been trained on the U++network. Classification techniques, like foot ulcer analysis, forecast a etiology. This study's primary goal was to establish a novel method for evaluating the likelihood that diabetes individuals may acquire foot ulcers by imaging analysis of existing foot ulcers. The data was preprocessed and segmented after the researchers gathered a collection of foot photographs and medical information from historical records of diabetes patients. The amount of normal and pathological diabetes was then determined from numerical and textual data by extracting characteristics from the segmented data using DFINET-AO. To detect foot ulc

关键词： Diabetic foot infection network with the adam optimizer Diabetic foot ulcer Pre-trained fast convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Implementation of Elliptic Curve Cryptosystem with Bitcoin Curves on SECP256k1, NIST256p, NIST521p, and LLL

Journal of ICT Standardization

引用

Journal of ICT Standardization 2023年第4期11卷 329-354页

作者： Ulla, Mohammed Mujeer Preethi Khan, Md Sameeruddin Sakkari, Deepak S. School of Computer Science and Engineering Presidency University Karnataka Bangalore India Department of Information Technology Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India Department of Computer Science and Engineering Sri Krishna Institute of Technology Bangalore India

Very recent attacks like ladder leaks demonstrated the feasibility of recovering private keys with side-channel attacks using just one bit of secret nonce. ECDSA nonce bias can be exploited in many ways. Some attacks on ECDSA involve complicated Fourier analysis and lattice mathematics. This paper will enable cryptographers to identify efficient ways in which ECDSA can be cracked on curves NIST256p, SECP256k1, NIST521p, and weak nonce, kind of attacks that can crack ECDSA and how to protect yourself. Initially, we begin with an ECDSA signature to sign a message using the private key and validate the generated signature using the shared public key. Then we use a nonce or a random value to randomize the generated signature. Every time we sign, a new verifiable random nonce value is created, and a way in which the intruder can discover the private key if the signer leaks any one of the nonce values. Then we use Lenstra–Lenstra–Lovasz (LLL) method as a black box, we will try to attack signatures generated from bad nonce or bad random number generator (RAG) on NIST256p, SECP256k1 curves. The combination of nonce generation, post-message signing, and validation in ECDSA helps achieve Uniqueness, Authentication, Integrity, and Non-Repudiation. The analysis is performed by considering all three curves for the implementation of the Elliptic Curve Digital Signature Algorithm (ECDSA). The comparative analysis for each of the selected curves in terms of computational time is done with the leak of nonce and with the Lenstra–Lenstra–Lovasz method to crack ECDSA. The average computational costs to break ECDSA with curves NIST256p, NIST521p, and SECP256k1 are 0.016, 0.34,0.46 respectively which is almost zero depicting the strength of the algorithm. The average computational costs to break ECDSA with curves SECP256K1 and NIST256p using LLL are 2.9 and 3.4 respectively. © 2023 River Publishers.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Empowering Consumers and Sustainability: A Global Review of Right to Repair Policies

Empowering Consumers and Sustainability: A Global Review of ...

引用

2024 International Conference on Distributed Systems, computer Networks and Cybersecurity, ICDSCNC 2024

作者： Preethish Kumar, M. Usha, B.A. Basavaraj, G.N. Mohan, B.A. Prithvi, G. Rajkumar Bms Institute of Technology and Management Department of Information Science and Engineering Bengaluru India Nagarjuna College of Engineering and Technology Department of Computer Science and Engineering Bengaluru India

ISBN: (数字)9798350375442

ISBN: (纸本)9798350375442

The 'Right to Repair' (R2R) movement has gained significant attention in recent years with the aim empowering consumers to fix their products rather than replacing them when they become faulty. This paper offers a comprehensive analysis of the impact of R2R policies on consumer rights, environmental sustainability, economic outcomes, social implications, and technological advancement in the digital era. Further, this paper discusses the role of open repair ecosystems in fostering innovation, facilitating aftermarket services, and empowering informed consumer choices. It examines the legal and regulatory frameworks surrounding R2R, including recent legislative initiatives at multiple levels. The paper concludes by advocating for R2R as a fundamental aspect of consumer rights and environmental stewardship, highlighting its potential to promote sustainability, foster innovation, and create a more equitable economy. © 2024 IEEE.

关键词： Sustainable development goals

来源：评论

学校读者我要写书评

暂无评论

Innovative Skin Melanoma Diagnosis using Deep Learning and African Gorilla Troops Optimizer 1

Innovative Skin Melanoma Diagnosis using Deep Learning and A...

引用

1st International Conference on Software, Systems and Information technology, SSITCON 2024

作者： Parthasarathi, P. Nivedha, S. Balamurugan, M. Yuvaraj, D. Siamala Devi, S. Sangeethaa, S.N. Bannari Amman Institute of Technology Department of Computer Science and Engineering Sathyamangalam India Bannari Amman Institute of Technology Department of Information Technology Sathyamangalam India Sona College of Technology Dpartment of Computer Science and Engineering Salem India Kongu Engineering College Department of Computer Science and Design Perundurai India Sri Eshwar College of Engineering Kuniamuthur Department of Information Technology Coimbatore India Bannari Amman Institute of Technology Sathyamangalam Department of Computer Science and Engineering Erode India

ISBN: (纸本)9798350352931

Skin melanoma, a dangerous kind of skin cancer, necessitates accurate identification and diagnosis to improve patient outcomes. The use of deep learning algorithms into medical imaging promises significant advancements in skin disease analysis, particularly melanoma diagnosis. This study looks at the usage of a novel optimisation technique, the African Gorilla Troops Optimizer (AGTO), to enhance deep learning models in the segmentation and analysis of skin images. The AGTO, which is based on African gorilla groups' social and hunting activities, is an effective approach of improving convolutional neural networks (CNNs) for accurate and reliable skin image segmentation. The proposed approach uses AGTO to distinguish melanoma lesions from benign skin disorders, which increases their identification. Extensive research on benchmark skin image datasets has confirmed the AGTO-enhanced deep learning model's durability and performance, emphasising its clinical use in dermatology and the proposed model shows 98 %accuracy. This work not only underlines the need of advanced optimisation techniques in medical image processing, but it also paves the way for more effective diagnostic tools for skin problems. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Network Anomaly Detection using Autoencoder on Various Datasets: A Comprehensive Review

引用

Recent Patents on engineering 2024年第9期18卷 63-77页

作者： Singh, Richa Srivastava, Nidhi Kumar, Ashwani Amity Institute of Information Technology Amity University Lucknow Campus Uttar Pradesh Lucknow India Department of Computer Science and Engineering School of Engineering and Technology Sharda University Greater Noida India

The scientific community is currently very concerned about information and communication technology security because any assault or network anomaly can have a remarkable collision on a number of areas, including national security, the storage of private data, social welfare, economic concerns, and more. As a result, many strategies and approaches for this goal have been developed over time, making the anomaly detection domain a large research subject. The primary concern of this patent study is to review the most crucial elements relating to anomaly detection, including an overview of background analysis and a core study on the most important approaches, procedures, and systems in the field. To make the structure of this survey easier to understand, the domain of anomaly detection was examined along with five dimensions: Detection methods in network traffic, objectives of the patent paper, various datasets used, accuracy, and open issues/gaps. The gap which has been identified after the survey can be extended as a future scope might be helpful for the researcher. © 2024 Bentham science Publishers.

关键词： Anomaly detection

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：