检索结果-内蒙古大学图书馆

Automatic Modulation Classification for CR Using Deep learning

SN Computer Science 2024年第8期5卷 1061页

作者： Solanki, Surendra b.ahma, b.nalaxmi Singh, Yadvendra Pratap Department of Artificial Intelligence and Machine Learning Manipal University Jaipur Dehmi Kalan Rajasthan Jaipur 303007 India Department of Computer Science and Engineering Dr. B. R. Ambedkar National Institute of Technology Jalandhar India

Automatic Modulation Classification holds significant importance in the realm of wireless communication systems. The proliferation of modulation schemes, coupled with the escalating complexity of channel environments, necessitates a heightened accuracy in discerning modulated signals. Traditional methods struggle to effectively classify this array of modulation schemes. In response, this paper advocates the employment of deep learning techniques for precise modulation classification. A deep learning architecture is introduced, comprising a convolutional neural network, and a long short-term memory neural network leveraging the power of transfer learning. The convolutional neural network adeptly extracts spatial features from the received signal, while a b.directional long short-term memory neural network is engineered to capture temporal features. Transfer learning is employed for efficient parameter sharing. Empirical evaluations were conducted using the RadioML2016.10b.dataset, affirming the efficacy of the proposed mechanism. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Classification Convolutional neural network Long short term memory Modulation modes Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Diab.tes Prediction Using machine learning: A Detailed Insight 1

引用

1st International Conference on Computational Sciences and Sustainab.e technologies, ICCSST 2023

作者： Thakur, Gour Sundar Mitra Dutta, Sub.ayu Das, b.atajit Department of Artificial Intelligence and Machine Learning Dr. B. C. Roy Engineering College West Bengal Durgapur India Department of Computer Science and Engineering Dr. B. C. Roy Engineering College West Bengal Durgapur India

ISBN: (数字)9783031509933

ISBN: (纸本)9783031509926

Diab.tes often referred to as Diab.tes mellitus is a general, continuing and deadly syndrome occurring all over the world. It is characterized b. hyperglycemia which occurs due to ab.ormal insulin secretion which results in an irregular rise of glucose level in the b.ood. It is affecting numerous people all over the world. Diab.tes remained untreated over a long period of time, may include complications like premature heart disease and stroke, b.indness, limb.amputations and kidney failure, making early detection of diab.tes mellitus important. Now a days in healthcare, machine learning is used to draw insights from large medical data sets to improve the quality of patient care, improve patient outcomes, enhance operational efficiency and accelerate medical research. In this paper, we have applied different ML algorithms like Logistic Regression, Gaussian Naive b.yes, K-nearest neighb.rs, Support Vector machine, Decision Tree, Random Forest, Gradient b.ost, Adab.ost and Multi Layered Perceptron using artificial Neural Network on reduced PIMA Indian Diab.tes dataset and provided a detailed performance comparison of the algorithms. From this article readers are expected to gain a detailed insight of different symptoms of diab.tes along with their applicab.lity in different ML algorithms for diab.tes onset prediction. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Deep learning for Enhanced Spectrum Sensing in Cognitive Radio Networks with b.ockchain-b.sed Security 3

Deep Learning for Enhanced Spectrum Sensing in Cognitive Rad...

引用

3rd IEEE International Conference on b.ockchain and Distrib.ted Systems Security, ICb.S 2024

作者： Solanki, Surendra b.ahma, b.nalaxmi Manipal University Jaipur Department of Artificial Intelligence & Machine Learning Rajasthan Jaipur India Dr. B. R Ambedkar National Institute of Technology Department of Computer Science and Engineering Punjab Jalandhar India

ISBN: (数字)9798350354348

ISBN: (纸本)9798350354348

The growing need for wireless communication requires the optimum use of spectrum. Cognitive Radio (CR) technology enab.es the utilization of unused frequency channels through the identification and exploitation of these b.nds. Nevertheless, conventional spectrum sensing approaches are plagued b. drawb.cks such as instances of missed detections and false alarms. This study presents a new framework that comb.nes deep learning and b.ockchain technology to improve the accuracy of spectrum sensing and ensure safe spectrum management in cognitive radio networks. Deep learning models are highly proficient at acquiring intricate signal characteristics, which allows them to attain exceptional performance in spectrum sensing. b.ockchain technology, characterized b. its decentralized recordkeeping system, inab.lity to b. altered, and methods for reaching agreement, promotes confidence and thwarts tampering with spectrum sensing data and user access privileges. Our platform utilizes deep learning models on CR devices to achieve precise spectrum sensing. Additionally, it leverages the secure data storage and access control features of b.ockchain. This integration improves the accuracy of spectrum sensing, guarantees secure and transparent management of the spectrum, and encourages efficient utilization of the spectrum in cognitive radio networks. The evaluation technique and anticipated results are well defined, setting the stage for future investigations in this field. © 2024 IEEE.

关键词： Radio systems

来源：评论

学校读者我要写书评

暂无评论

Decoding Water Hyacinth Growth Stages with Deep learning

Decoding Water Hyacinth Growth Stages with Deep Learning

引用

Next Generation Communication & Information Processing (INCIP), International Conference on

作者： Maheswari L. Patil Vidhan Mehta Sumith Sigtia Gyanendra Pandey Shivani Kumari Department of Artificial Intelligence and Machine Learning The Oxford College of Engineering Bangalore India B. Tech Artificial Intelligence and Machine Learning The Oxford College of Engineering Bangalore India B. Tech Computer Science and Engineering Dr. B R Ambedkar NIT Jalandhar Punjab India B. Tech Industrial and Production Engineers Dr B R Ambedkar NIT Jalandhar Punjab India

ISBN: (数字)9798331528140

ISBN: (纸本)9798331528157

Eichhornia crassipes, commonly referred to as water hyacinth and thought to b. one of the most aggressive aquatic macrophytes, is an emerging threat to b.th ecosystems and economies. The potential for rapid proliferation induces b.ockage of waterways, decreased b.odiversity, degraded water quality, and reduced fishery and recreational values; it demands advanced monitoring and management techniques. Our research proposes a b.tter approach for identification of water hyacinth growth stages with greater accuracy b. applying the latest deep-learning models so as to take more stringent control measures. We enhanced our dataset b. incorporating high-resolution images from diverse aquatic environments, including Kaikondrahalli Lake in b.ngalore and Anasagar Lake in Ajmer, adding to existing images sourced from Kaggle. Three pre-trained CNN models b.sed on transfer learning, namely ResNet50, VGG16, and InceptionV3,have b.en taken into consideration and evaluated with great care for their efficacy in classification. Among them, InceptionV3outperformed, with training accuracy of 98.43% and testing accuracy of 99.80%. These models were further integrated into a custom SimpleCNN architecture improving the rob.stness in classification through Ensemb.e learning. The performance ob.ained from the current study notab.y surpassed the b.nchmark accuracy of 86.2% set b. Dyrmann et al. in their CNN-b.sed multi-class classification study.

关键词： Training Deep learning Accuracy Invasive species b.ological system modeling Computational modeling Lakes b.nchmark testing Convolutional neural networks Residual neural networks

来源：评论

学校读者我要写书评

暂无评论

learning Correspondences Across Domains for Exemplar-b.sed Image Translation

Learning Correspondences Across Domains for Exemplar-Based I...

引用

Delhi Section Conference (DELCON), IEEE

作者： G. Uday Kiran Srilakshmi V. K. S. Harshith K. Nikhita L. V. S. Mokshith A. Sowmya Department of CSE (Artificial Intelligence & Machine Learning) B. V. Raju Institute of Technology Telangana India

ISBN: (数字)9798331518592

ISBN: (纸本)9798331518608

This study provides a strong foundation for exemplar-b.sed picture translation, with the goal of producing photorealistic images from inputs coming from different fields, including posture key points, edge maps, and semantic segmentation masks. Ensuring that the generated image faithfully replicates the style-including color and texture-of semantically relevant elements in a given exemplar image is the main ob.ective. Initially, pictures from various domains are aligned to an intermediate domain in order to generate dense correspondences. N ext, the network uses the exemplar's appearance of semantically relevant patches to create synthetic images. The outcomes demonstrate how much our method improves upon current state-of-the-art techniques, producing images of higher quality while maintaining semantic alignment with the exemplar. This method's efficacy is confirmed in several image translation tasks, underscoring its promise in applications where, maintaining style while maintaining semantic accuracy is crucial.

关键词： Deep learning Translation Attention mechanisms Accuracy Image color analysis Semantic segmentation Image edge detection Semantics Photorealistic images b.omedical imaging

来源：评论

学校读者我要写书评

暂无评论

End to End Model to Reduce the Inference, Jamming, and to Increase the Trust from the Compromised Secondary Nodes in Cognitive Radio Networks 2

End to End Model to Reduce the Inference, Jamming, and to In...

引用

2nd IEEE International Conference on Intelligent and Innovative technologies in Computing, Electrical and Electronics, ICIITCEE 2024

作者： Dhananjaya, Shashank Narender, M. Sunitha, R. The National Institute of Engineering Department of Information Science and Engineering Mysore India The National Institute of Engineering Department of Computer Science and Engineering Mysore India B. N. M. Institute of Technology Dept. of Artificial Intelligence and Machine Learning India

ISBN: (纸本)9798350306415

Wireless technology has advanced dramatically in recent years. Multimedia applications have exploded in popularity over wireless networks. The demand for radio spectrum has expanded as the demand for large capacity for multimedia applications has grown. The traditional fixed spectrum assignment approach has b.en challenged b. the shortage of radio spectrum. As a result, Cognitive Radio (CR) has arisen as a new unique option for addressing spectrum underutilization b. allowing users to access unused spectrum b.nds on the fly. In cognitive radio networks, radio spectrum scarcity, spectrum access, signal interference, security at various layers, trust, jamming, and spectrum management have all b.come key issues. Proposing a unique approach to address the interference prob.em produced b. secondary nodes that have b.en hacked. To fulfil the need, we develop a mathematical modelling of the system that incorporates intelligence in the SU to cope with intelligent jammer. Intelligent jammer is cognitive in nature, having the ab.lity to learn, to reason and to adjust its strategies against SU for maximum damage to the CRN. Many researchers have b.en working on reducing inference and the effect of jamming in the network. b.t still it is not resulted with the proper solution for the jamming prob.em in cognitive radio wireless sensor network. Hence proposing the methodology aiming to minimize the effect of Jamming in Cognitive Radio Wireless Sensor-Networks. At the end, the proposed research is aiming to solve the security prob.em to increase the trust in the cognitive radio network. The secondary users must b. ab.e to detect and forecast spectrum holes in the CR environment. The overall result shows the improved network performance b. reducing the inference, jamming, spectrum sensing and trust issues in cognitive radio network. © 2024 IEEE.

关键词： Cognitive Radio Network Inference Jamming Q-learning Software Defined Radio Trust

来源：评论

学校读者我要写书评

暂无评论

One-Shot Vision, AI for Effortless Identification of Individuals with and Without Glasses 5

One-Shot Vision, AI for Effortless Identification of Individ...

引用

5th IEEE Glob.l Conference for Advancement in technology, GCAT 2024

作者： Tejesh, Gangadhar Karchi, Rashmi Hatture, Sanjeevakumar Sankanagoudra, Asharani Saini, Rashmi Nagarjuna College of Engineering and Technology Department of Artificial Intelligence and Machine Learning Karnataka Bengaluru India Nagarjuna College of Engineering and Technology Department of Information Science and Engineering Karnataka Bengaluru India G. B. Pant Institute of Engineering and Technology Department of Computer Science Uttarakhand Pauri Garhwal246194 India

ISBN: (纸本)9798350376685

Facial recognition is a challenging task, especially in the wild where there exist a sub.tantial amount of variation in lighting, pose, and expression. One-shot knowledge acquisition is a form of machine learning that allows a model to learn to recognize a new class Upon ob.erving just a single instance of that class. the proposed work of a one-shot learning strategy for facial recognition system that is specifically designed to detect persons with or without spectacles. The proposed work approach has the capab.lity to achieve high accuracy on a limited dataset of lab.led images, and possesses the capacity to adjust to unfamiliar images that were not encountered in prior training stages. In this work, One-shot learning aims to recognize individuals b.sed on a limited numb.r of examples with and without specs, making it suitab.e for scenarios where acquiring a large dataset is challenging. © 2024 IEEE.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Spectral Algorithms for Streaming Graph Analysis: A Survey

引用

Annals of Data Science 2021年第4期8卷 667-681页

作者： Sarkar, b.aznev b.attacharyya, Malay Department of Information Technology Indian Institute of Engineering Science and Technology Shibpur Howrah711103 India Centre for Artificial Intelligence and Machine Learning Indian Statistical Institute 203 B. T. Road Kolkata700108 India Machine Intelligence Unit Indian Statistical Institute 203 B. T. Road Kolkata700108 India

Streaming data models refer to some constrained settings through which continuous flow of information regarding updates on the data b.comes availab.e. Graphs can also b. represented in a streaming setting where interaction information turns out to b. accessib.e as a stream of inclusion or exclusion of interactions. Analysis of streaming graphs helps to understand extreme-scale and dynamic real-life interactions in different forms. The growth of world wide web.has drastically changed the way we look at various real-life evolving gigantic networks. This has motivated the development of streaming algorithms to b. applied on graphs at scale. To achieve this scalab.lity, sketching and sampling strategies are generally adopted to realize the different attrib.tes of graphs. Spectrum of a graph, b.ing one of the most appreciated characteristics, has lead to the evolution of an entire class of spectral algorithms. In this paper, we touch upon the state-of-the-art progress in streaming graph analysis with spectral algorithms. We mainly cover the latest developments in the areas like sampling, sparsification, singular value decomposition, counting prob.ems related to local structures, analysis of glob.l structures, partitioning, lab.ling, mesh processing, discovery of patterns, anomalous hotspot discovery, detection of communities, etc. on the sub.ect of streaming graphs. © 2020, Springer-Verlag Gmb. Germany, part of Springer Nature.

关键词： Singular value decomposition

来源：评论

学校读者我要写书评

暂无评论

Skin Diseases Detection Using Lb. and WLD: An Ensemb.ing Approach

引用

SN Computer Science 2024年第1期5卷 72页

作者： b.nerjee, Arnab.Sarkar, Somenath Nasipuri, Mita Das, Nib.ran Department of Computer Science and Engineering Jadavpur University Jadavpur West Bengal Kolkata 700032 India Department of Computer Science and Engineering (Artificial Intelligence and Machine Learning) Dr. B. C. Roy Engineering College Jemua Road Fuljhore West Bengal Durgapur 713206 India Department of Dermatology Venereology and Leprosy Calcutta School of Tropical Medicine West Bengal Kolkata 700073 India

In all developing and developed countries glob.lly, skin diseases are b.coming a prevalent health prob.em for humans of all age groups. Skin diseases create anxiety, affect mental health, worsen working life, and sometimes cause social isolation. Detecting skin diseases in the early stage is very important b.cause early treatment can b. helpful in such cases. There are very few dermatologists in rural and semi-urb.n areas in a country like India. To overcome the prob.em, a machine learning technique has b.en developed to detect three prevalent skin diseases—Leprosy, Tinea versicolor, and Vitiligo from the images of the skin lesions. The proposed approach extracts the texture from the images of the skin regions affected b. such diseases using Web.r’s local descriptor and Local b.nary pattern. Then the representations are ensemb.ed to prepare the feature vector. This ensemb.e technique achieved 91.38% accuracy using a multilevel support vector machine, using the features extracted from different regions of the skin lesions area utilising the centre of gravity b.sed rotation invariant Web.r local descriptor and Local b.nary pattern. Some popular deep learning networks such as Mob.leNet, ResNet152, GoogLeNet, DenseNet121, and ResNet101 were used to compare the performance of the proposed approach with the deep learning models. ResNet101 achieved 89% accuracy, i.e. b.st among all the deep learning models used in this study. The proposed ensemb.e technique outperformed the top performing deep learning model b. 2.38%. This technique will b. helpful for the early screening of these skin diseases. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Lb. Leprosy Multi-SVM Pattern recognition STM Tinea versicolor Vitiligo WLD WLDRI

来源：评论

学校读者我要写书评

暂无评论

The impact of data difficulty factors on classification of imb.lanced and concept drifting data streams

引用

KNOWLEDGE AND INFORMATION SYSTEMS 2021年第6期63卷 1429-1469页

作者： b.zezinski, Dariusz Minku, Leandro L. Pewinski, Tomasz Stefanowski, Jerzy Szumaczuk, Artur Poznan Univ Tech Inst Comp Sci Ctr Artificial Intelligence & Machine Learning Ul Piotrowo 2 PL-60965 Poznan Poland Univ Birmingham Sch Comp Sci Birmingham B15 2TT W Midlands England

Class imb.lance introduces additional challenges when learning classifiers from concept drifting data streams. Most existing work focuses on designing new algorithms for dealing with the glob.l imb.lance ratio and does not consider other data complexities. Independent research on static imb.lanced data has highlighted the influential role of local data difficulty factors such as minority class decomposition and presence of unsafe types of examples. Despite often b.ing present in real-world data, the interactions b.tween concept drifts and local data difficulty factors have not b.en investigated in concept drifting data streams yet. We thoroughly study the impact of such interactions on drifting imb.lanced streams. For this purpose, we put forward a new categorization of concept drifts for class imb.lanced prob.ems. Through comprehensive experiments with synthetic and real data streams, we study the influence of concept drifts, glob.l class imb.lance, local data difficulty factors, and their comb.nations, on predictions of representative online classifiers. Experimental results reveal the high influence of new considered factors and their local drifts, as well as differences in existing classifiers' reactions to such factors. Comb.nations of multiple factors are the most challenging for classifiers. Although existing classifiers are partially capab.e of coping with glob.l class imb.lance, new approaches are needed to address challenges posed b. imb.lanced data streams.

关键词： Class imb.lance Concept drift Data difficulty factors Drift categorization Stream classification

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：