检索结果-内蒙古大学图书馆

A cluster and label approach for classifying imbalanced data streams in the presence of scarcely labelled data

International Journal of Business Intelligence and data Mining 2022年第4期21卷 443-464页

作者： Bhowmick, Kiran Narvekar, Meera Department of Computer Engineering D J Sanghvi College of Engineering Mumbai400056 India

Classifying imbalanced data streams is often a challenging task primarily due to the continuous flow of infinite data and due to the unavailability of class labels. The problem is two-fold when the stream is imbalanced in nature. due to the characteristics of data streams, it is impossible to store and process the data and deal with imbalance. There is a need to provide a solution that can consider the unavailability of class labels and classify the imbalanced data streams. This paper proposes a semi-supervised learning (SSl)-based model to classify scarcely labelled imbalanced data streams. A modified cluster and label SSl approach that uses expectation maximisation for clustering and similarity-based label propagation for labelling the unlabelled clusters is proposed. The model also employs a novel imbalance sensitive cluster merge technique to deal with the imbalance data. The results prove that the model outperforms standard stream classification algorithms. Copyright © 2022 Inderscience Enterprises ltd.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Spatio Temporal Tourism Tracking System Based on Adaptive Convolutional Neural Network

引用

computer Systems Science & engineering 2023年第6期45卷 2435-2446页

作者： l.Maria Michael Visuwasam d.Paul Raj Department of Computer Science and Engineering Rajalakshmi Institute of TechnologyChennaiTamil Nadu600104India Department of Computer Science and Engineering R.M.D.Engineering CollegeChennaiTamil Nadu601204India

Technological developments create a lot of impacts in the tourism *** big data technologies and programs generate opportunities to enhance the strategy and results for transport ***,there is a difference between technological advances and their integration into the methods of tourism *** rising popularity of Freycinet National Park led to a master plan that would not address cultural and environmental *** study addresses the gap by using a synthesized application(app)for demographic surveys and Global Navigation Satellite System(GNSS)technology to implement research *** article focuses on managing visitors within the famous Freycinet National *** comprehensive structured data were analyzed in three phases,(1)identifying groups of visitors who are more likely to use the walking trails,(2)those who are more and less likely to visit during/peak crowding times,and(3)finally creating an integrated Spatio-temporal dependency model via a machine-based learning system for real-time *** research examines innovative techniques that can offer energy resources to managers and tourism agencies,especially in detecting,measuring,and potentially relieving crowding and over-tourism.

关键词： Spatio-temporal dependency machine-based learning global navigation satellite system(GNSS)technology smartphones

来源：评论

学校读者我要写书评

暂无评论

lung Sounds Identification based On Transfer learning Approaches : A Review 6

Lung Sounds Identification based On Transfer Learning Approa...

引用

6th International Conference on Electronics, Communication and Aerospace Technology, ICECA 2022

作者： Vasava, Rajeshree Parsingbhai Joshiara, Hetal A. L D College of Engineering Computer Engineering Department Gujarat Ahmedabad India

ISBN: (纸本)9781665482714

'lung diseases are now considered as one of the fatal diseases across the globe. However, early detection of lung disease may help in providing earlier treatment since most cases of lung diseases are only detected after they have progressed to advanced stage. Today's healthcare system relies on the recent technological advancements. lung sound analysis plays a crucial role in the diagnosis of lung disease. Further, the successful navigation of medical system requires the ability to acquire new information and utilize it in new contexts. To perform classification, this research work presents several transfer learning strategies, including AlEXNET, VGGNET, and RES NET for analyzing the lung sounds. To complement the techniques, a Transfer learning model that incorporates a Modified RESNET with a Mel spectrogram of lung sound signals are used to perform classification. These transfer learning models perform efficiently in classifying the lung sounds, which can be later used to diagnose respiratory diseases. This research study analyzes several transfer learning methods and discuss their benefits and drawbacks in identifying four distinct types of lung sounds. Finally, the further research directions on the identification of lung sounds are discussed.' © 2022 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

A Review on Transfer learning and Generative Adversarial Networks for Classification of All 6

A Review on Transfer Learning and Generative Adversarial Net...

引用

6th International Conference on Electronics, Communication and Aerospace Technology, ICECA 2022

作者： Mepani, Ketan domadiya, Nikunj L D College of Engineering Computer Engineering Department Gujarat Ahmedabad India

ISBN: (纸本)9781665482714

leukemia is classified as either myelogenous (also called myeloid) or lymphocytic depending on which types of white blood cells are affected. Most current AI techniques for medical image analysis rely on supervised learning, which contains a substantial amount of labelled data. Medical images annotations are typically pricey and not readily available in large quantities for this limitation GAN model require to generate images in medical field. There are deep learning has many vital applications, including medical image processing, which is anticipated to significantly reduce the burden of doctors. The ability of Generative Adversarial Networks is to produce high-quality visual samples from the images in less time. This research examines the state of Acute lymphoblastic leukemia (All) prediction approach with Generative Adversarial Network (GAN) research in the field of medical imaging and examines various transfer learning models. This research also discussions upcoming research leukemia and problems of GAN for medical image analysis. © 2022 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

A Secure IoT-Cloud Based Healthcare System for disease Classification Using Neural Network

引用

computer Systems Science & engineering 2022年第4期41卷 95-108页

作者： M.Vedaraj P.Ezhumalai Department of Computer Science and Engineering R.M.D.Engineering CollegeKavaraipettai601206TamilnaduIndia

The integration of the Internet of Things(IoT)and cloud computing is the most popular growing technology in the IT *** integrated cloud com-puting technology can be used in smart cities,health care,smart homes,environ-mental monitoring,*** recent days,IoT integrated cloud can be used in the health care system for remote patient care,emergency care,disease prediction,pharmacy management,***,still,security of patient data and disease predic-tion accuracy is a major *** machine learning approaches were used for effective early disease ***,machine learning takes more time and less performance while classiﬁ*** this research work,the Attribute based Searchable Honey Encryption with Functional Neural Network(ABSHE-FNN)framework is proposed to analyze the disease and provide stronger security in IoT-cloud healthcare *** this work,the Cardiovascular disease and Pima Indians diabetes dataset are used for heart and diabetic disease classiﬁ***-ally,means-mode normalization removes the noise and normalizes the IoT data,which helps to enhance the quality of ***ﬁed linear Unit(RlU)was applied to adjust the feature weight to reduce the training cost and error classiﬁ-*** proposed ABSHE-FNN technique provides better security and achieves 92.79%disease classiﬁcation accuracy compared to existing techniques.

关键词： Honey encryption functional neural network rectiﬁed linear unit feature selection classiﬁcation

来源：评论

学校读者我要写书评

暂无评论

Adaptive Marine Predator Optimization Algorithm(AOMA)-deep Supervised learning Classification(dSlC)based IdS framework for MANET security

引用

Intelligent and Converged Networks 2024年第1期5卷 1-18页

作者： M.Sahaya Sheela A.Gnana Soundari Aditya Mudigonda C.Kalpana K.Suresh K.Somasundaram Yousef Farhaoui Department of Electronics and Communication Engineering Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and TechnologyChennai 600069India Department of Computer Science and Engineering Saveetha School of EngineeringSIMATSChennai 602105India JNIAS School of Planning and Architecture Hyderabad 500034India Department of Computer Science and Engineering NPR College of Engineering and TechnologyNatham Dindigul 624401India Department of Computer Science and Engineering PSNA College of Engineering and TechnologyPoolangulathupatti 620009India Department of Computer Science and Engineering Sri Muthukumaran Institute of TechnologyChennai 600069India Department of Computer Science Moulay Ismail UniversityMeknes 5003Morocco

due to the dynamic nature and node mobility,assuring the security of Mobile Ad-hoc Networks(MANET)is one of the difficult and challenging tasks *** MANET,the Intrusion detection System(IdS)is crucial because it aids in the identification and detection of malicious attacks that impair the network’s regular *** machine learning and deep learning methodologies are used for this purpose in the conventional works to ensure increased security of ***,it still has significant flaws,including increased algorithmic complexity,lower system performance,and a higher rate of ***,the goal of this paper is to create an intelligent IdS framework for significantly enhancing MANET security through the use of deep learning ***,the min-max normalization model is applied to preprocess the given cyber-attack datasets for normalizing the attributes or fields,which increases the overall intrusion detection performance of ***,a novel Adaptive Marine Predator Optimization Algorithm(AOMA)is implemented to choose the optimal features for improving the speed and intrusion detection performance of ***,the deep Supervise learning Classification(dSlC)mechanism is utilized to predict and categorize the type of intrusion based on proper learning and training *** evaluation,the performance and results of the proposed AOMA-dSlC based IdS methodology is validated and compared using various performance measures and benchmarking datasets.

关键词： Intrusion detection System(IdS) Security Mobile Ad-hoc Network(MANET) min-max normalization Adaptive Marine Predator Optimization Algorithm(AOMA) deep Supervise learning Classification(dSlC)

来源：评论

学校读者我要写书评

暂无评论

A Comparative Analysis of denoising PCG Signals using Adaptive Wiener-Kalman Filtering 8

A Comparative Analysis of Denoising PCG Signals using Adapti...

引用

8th IEEE International Conference on Computational System and Information Technology for Sustainable Solutions, CSITSS 2024

作者： Pandiaraj, A. Ramshankar, N. Gnanasekar, A. Arunchandran, R. Azariah John, B.S. Febin, C. Srm Institute of Science and Technology Department of Computing Technologies Kattankulathur Chennai India R.M D. Engineering College Department of Computer Science and Engineering India R.M D. Engineering College Department of Computer Science and Engineering kavaraipettai India R.M.D Engineering College Chennai India

ISBN: (纸本)9798331505462

Cardiovascular disease (CVd) is the group of disorder occurs on heart and blood vessel, and they are coronary heart disease, cerebrovascular disease, rheumatic heart disease, etc. Particularly people under the age of 70 are mostly affected by this disease. Earlier cardiologist analyse phonocardiography (PCG) signals to know the condition of heart. Because of the undesirable noise present in PCG signal makes complication in diagnosis by experts. This study analyse and denoising heart sound using five different techniques namely Short-Time Fourier Transform (STFT), Empirical Mode decomposition (EMd), Recurrent Neural Network (RNN), weiner filter (WF), adaptive Wiener-Kalman filtering (AWKF). There are lot of noise removal techniques available as discussed in the literature, failed to achieve higher performance in denoising audio signal. The developed denoising techniques were applied on various pathological heart sounds and on heart sound recorded in a noisy environment. The AWKF filtering has great impact on removing distortion and interference present on the signal. This method reserves the major characteristics of heart beat sound. The experimental results showed that AWKF acquired higher SNR, PSNR, lower RMSE and great denoising effect. © 2024 IEEE.

关键词： Wiener filtering

来源：评论

学校读者我要写书评

暂无评论

Effect of Sustainable Column Materials on Compressibility Characteristics of decomposed MSW Through Model Study 9th

Effect of Sustainable Column Materials on Compressibility Ch...

引用

9th Indian Young Geotechnical Engineers conference, 9IYGEC 2023

作者： Shah, Manish V. Shah, Alpa J. Jha, Abhishek Gajjar, Nirali Department of Applied Mechanics L. D. College of Engineering Ahmedabad India

ISBN: (纸本)9789819769872

Over a period of time, municipal solid waste decomposes and converts into material having 70–80% soil content. MSW has a sandy gradation, but it has a water affinity, which makes it more compressible. The composition of this waste varies from place to place, as do its geotechnical properties. This waste material can be used as fill material for construction sites, or old landfills themselves can be used as construction sites. However, because of its organic content and fibrous composition, it is compressible in nature and requires long-term geotechnical techniques to reduce compressibility and increase load carrying capacity. As per the Central Pollution Control Board (CPCB), only 28% of collected waste is treated, and the rest is dumped in landfills, which need to be sustainably utilized. The composition of MSW in India is approximately 40–60% compostable, 30–50% inert, and 10–30% recyclable. This will be a complete dual task of waste utilisation and fill material independence from borrow pits. In India, the rate of generation of C&d waste annually increases by 5%, and approximately 40% of fly ash remains unutilized every year, which needs to be utilized. The objective of the present research work is to determine the load-settling characteristics of old MSW by infusing sand, fly ash, lime and C&d waste columns, respectively, from the top. The present work is mainly focused on the improvement in load settlement characteristics like axial load carrying capacity, load resistance, settlement reduction factor, and stress concentration ratio obtained due to the infusion of various column materials. © The Author(s), under exclusive license to Springer Nature Singapore Pte ltd. 2025.

关键词： Fly ash

来源：评论

学校读者我要写书评

暂无评论

Smart Contracts in Real Estate: Enhancing Efficiency, Security, and Fraud Prevention Through Blockchain Technology - Modified Proof of Authorization (M-POA) 2

Smart Contracts in Real Estate: Enhancing Efficiency, Securi...

引用

2nd IEEE International Conference on Emerging Research in Computational Science, ICERCS 2024

作者： Subbarayudu Hemalatha, M. Prathyusha Engineering College Department of Information Technology Chennai India R.M.D Engineering College Department of Computer Science and Engineering Chennai India

ISBN: (数字)9798331534967

ISBN: (纸本)9798331534950

The real estate market is gradually changing with the pace of technology enhancement. While modernization with processes such as online platforms, virtual tours, and eSignatures has made some progress in this industry, a lot of challenges lie ahead, especially in security and fraud. This article addresses all these issues through the introduction of a new real estate ecosystem using blockchain technology but mainly with the Proof of Authorization (PoA) consensus mechanism. Blockchain technology offers an immutable ledger system whereby all property data and transactions are permanently recorded and verified. However, our research goes a step further in utilizing PoA. Unlike blockchain open models, PoA participation is restricted to only authorized entities within the network. They go through rigorous verification procedures, thus making fraudulent activities close to impossible under public and permission less models. By employing PoA, create a trust framework where only authenticated participants can transact on the system. This very much minimizes the realm potential to be governed by fraud. In short, the study used and empowered by blockchain, and security backed by PoA, is developing much more secure, transparent, and efficient setup of real estate transactions, developing trust and confidence within the stakes toward a future where real estates' transaction would be fast, secure, and fraud-free. With this innovation, the business of real estate is moving in a direction that is more effective, secure, and trustful. © 2024 IEEE.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Model Study of Reinforced Earth Wall Using dune Sand as a Backfill Material 9th

Model Study of Reinforced Earth Wall Using Dune Sand as a Ba...

引用

9th Indian Young Geotechnical Engineers conference, 9IYGEC 2023

作者： Shah, Manish V. Shah, Alpa J. Kalsariya, Vimal Shukal, Sparsh Department of Applied Mechanics L. D. College of Engineering Ahmedabad India

ISBN: (纸本)9789819766420

As reinforced earth walls are more durable and aesthetically better finished when compared to conventional retaining walls, the flexible nature of reinforced earth mass enables a reinforced earth wall to withstand large differential settlements without distress. Reinforced earth walls are consequently economical when the height of the structure is large or ground conditions are unfavorable and suitable backfill materials are locally available. The main objective of the research is to evaluate the feasibility of dune sand as a sustainable fill material for reinforced earth walls through the infusion of synthetic reinforcement at suitable positions. dune sand from Jaisalmer district, Rajasthan, is used as a backfill material for reinforced earth walls. For this purpose, load settlement and load–displacement tests were carried out on dune sand and River Sand, with a mix proportion of 1(dS):1(RS), 1.5(dS):1(RS), and 2(dS):1(RS) using a large-scale model test setup. To measure the displacement and settlement, dial gauges were set up in the RE wall model to measure the vertical settlement of the backfill material and the lateral displacement of the RE wall. The vertical pressure distribution at the base of the RE wall using three different methods: Uniform pressure distribution, Trapezoidal pressure distribution, and Meyerhof’s pressure distribution, Vertical stress distribution on horizontal and vertical planes, active earth pressure were calculated for the justification of the experimental results. The results depicted a mixture of 1(dune Sand):1(River Sand) to be satisfactory. With the increase in the percentage of dune sand in the backfill, the composition shows an increase in lateral displacement. The vertical settlement of 2(dune Sand):1(River Sand) is much less compared to other proportions. © The Author(s), under exclusive license to Springer Nature Singapore Pte ltd. 2025.

关键词： Sand

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：