检索结果-内蒙古大学图书馆

A semi-supervised clustering-based classification model for classifying imbalanced data streams in the presence of scarcely labelled data

引用

International Journal of Business Intelligence and data Mining 2022年第2期20卷 170-191页

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

data streams are potentially infinite in length, fast changing and scarcely labelled. It is practically impossible to label all the observed instances. Online frameworks for classifying data streams are generally supervised in nature assuming the availability of labelled data and hence cannot be used for data streams. Semi-supervised learning (SSl) addresses this problem of scarcely labelled data by using large amount of unlabelled data together with labelled data to build classifiers. data streams may also suffer from the problem of imbalanced data. Previous works in learning from data streams have analysed problems of imbalanced data. But to the best of our knowledge no work has applied semi-supervised learning approaches for classifying imbalanced data streams so far. This paper proposes a model using a semi-supervised clustering technique to classify an imbalanced data stream in the presence of scarcely labelled data. The results prove that the model outperforms many state-of-the-art techniques. © 2022 Inderscience Enterprises ltd.

关键词： Cluster analysis

来源：评论

学校读者我要写书评

暂无评论

A Hybrid U-Net with Active Contours for Plant leaf disease Segmentation and Classification 3

A Hybrid U-Net with Active Contours for Plant Leaf Disease S...

引用

3rd International Conference on Electronics and Renewable Systems, ICEARS 2025

作者： Sivamurugan, J. Naveen, G. Rajalakshmi, d. Reddy, P. Venkata Subba Taher, Shaik deepak, Sannapu Madha Institute of Engineering and Technology Department of Computer Science and Engineering Chennai India Madha Institute of Engineering and Technology Department of Electronics and Communication Engineering Chennai India R.M.D. Engineering College Department of Computer Science and Engineering Thiruvallur India

ISBN: (纸本)9798331509675

The economic growth of a nation entirely depends upon the agriculture and agricultural products. In developing countries like India, agriculture is the primary source of income and its contributing 17% to the total GdP. There are plenty of factors lead to plant disease which impacts the quality and yield of plants. Though manual method of detection is time consuming and it may have chance for errors. This method is not enough to identify and limit the spread of plant disease. To establish an automated plant disease detection in farms will reduce the risk of plant disease and promotes real-time monitoring of crops in a daily basis. Artificial Intelligence (AI) took part in supporting farmers to get instant solution in selection of fertilizers, classifying the quality of agricultural products, weather prediction and soil nutrient level detection. In this study, we proposes a novel segmentation approach namely Hybrid U-Net with active contours to segment the disease affected portion on leaf which support farmers to identify disease at early stage. This study provides a comprehensive analysis of plant disease segmentation by proposed method with conventional approaches. The publically available dataset is chosen for this analysis and performance of conventional studies was compared. This study presented current trends of plant disease segmentation and several other image classification techniques. Experimental results evaluating that the proposed study improved segmentation better than conventional methods. © 2025 IEEE.

关键词： Wiener filtering

来源：评论

学校读者我要写书评

暂无评论

Enhancing Web Security: An Advanced Automated Kitterman Tool for Comprehensive Network Vulnerability detection

Enhancing Web Security: An Advanced Automated Kitterman Tool...

引用

2024 IEEE International Students' Conference on Electrical, Electronics and computer Science, SCEECS 2024

作者： Sasikumar, R. Anita, C.S. Rajalakshmi, d. Sudharson, K. Alekhya, Badi Kumar, N. Sathish R.M.D. Engineering College Department of Computer Science and Engineering Chennai India R.M.D. Engineering College Department of Artificial Intelligence and Machine Learning Chennai India

ISBN: (纸本)9798350348460

Strong security is essential in the ever-changing world of web applications to ward off potential dangers. To identify various network vulnerabilities like Cross-Site Scripting, database Injection, Information disclosure, Subdomain Enumeration, Cache deception, Banner Grabbing, Technology Fingerprinting, Apache denial-of-Service, Apache Struts Remote Code Execution, and Clickjacking, this paper presents a novel automated Kitterman tool. The application uses a powerful crawler to extract links and systematically find vulnerabilities using a URl input. Our investigation shows that our technology outperforms all previous tools with an astounding output level of 91.8%. With the proactive features of our automated Kitterman tool, you can fortify your online defences and make sure that your web applications are resilient against a wide range of possible threats. © 2024 IEEE.

关键词： automated kitterman tool cross-site scripting database injection network vulnerability detection web security

来源：评论

学校读者我要写书评

暂无评论

Plant Pathology detection for Massive Heterogeneous data Using deep learning 14

Plant Pathology Detection for Massive Heterogeneous Data Usi...

引用

14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023

作者： Chaudhari, Avinash Jani, Kuntesh Patel, Sunil Modasa Gujarat Technological University Government Engineering College Information Technology Department Modasa India Gujarat Technological University L.D. College of Engineering Information Technology Department Ahmedabad India Gujarat Technological University L.D. College of Engineering Computer Engineering Department Ahmedabad India

ISBN: (纸本)9798350335095

The manual inspection of plant disease is a difficult and time-consuming task that requires expertise in the area of plant pathology which is not always available. deep learning models have shown significant efficiency in solving image classification problems. They can be used in the field of precision agriculture for disease management tasks. State-of-the-art deep learning models are used in several studies to automatically detect diseases based on the plant leaves symptoms. Most of the studies have been carried out on single or limited plants. In this study large dataset having a total number of 1,02,113 images is created by combining 16 openly available datasets. A comparative performance analysis of three CNN models, ResNet50, MobileNetV2, and InceptionV3 has been carried out after training with the dataset. InceptionV3 has achieved the highest classification accuracy of 0.90. MobileNetV2 has less training time compared to others. © 2023 IEEE.

关键词： large dataset

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Image Analysis for Precision diagnosis and Recognition Using Cutting-Edge Visual Encoding

Revolutionizing Image Analysis for Precision Diagnosis and R...

引用

2024 IEEE International Students' Conference on Electrical, Electronics and computer Science, SCEECS 2024

作者： Rajalakshmi, d. Anita, C.S. Sasikumar, R. Sudharson, K. Alekhya, Badi Rose, S. Remya R.M.D. Engineering College Department of Computer Science and Engineering Chennai India R.M.D. Engineering College Department of Artificial Intelligence and Machine Learning Chennai India

ISBN: (纸本)9798350348460

This groundbreaking study introduces a revolutionary image analysis method, showcasing unprecedented accuracy in precision diagnosis and recognition. The innovative approach seamlessly integrates feature detection and description, demonstrating exceptional proficiency in identifying crucial local features. The advanced visual encoding architecture, surpassing conventional methods, utilizes intricate convolutional layers and the renowned Haar algorithm, achieving a remarkable 99% success rate. This comprehensive suite of advancements propels image analysis to new heights, with potential applications ranging from medical diagnostics to facial recognition. Strongly accepted for its cutting-edge techniques and impressive success rate. © 2024 IEEE.

关键词： facial recognition feature detection image analysis precision diagnosis visual encoding

来源：评论

学校读者我要写书评

暂无评论

deep learning model for smart wearables device to detect human health conduction

引用

Measurement: Sensors 2024年 36卷

作者： Yashwantbhai, Rathod Hiral Chande, Haresh dhanji Makwana, Sachinkumar Harshadbhai Prajapati, Payal Gondalia, Archana darji, Pinesh Arvindbhai Computer Science & Engineering Department Government Engineering College Patan India Computer Engineering Department L.D. College of Engineering Ahmadabad India

With the proliferation of smart wearables, motion wristbands provide a wealth of data essential for comprehending the dynamic nature of health. However, outlier detection is typically necessary due to the presence of unknown outliers in their multidimensional activity data. Conventional approaches frequently result in incorrect object identification due to the curse of dimensionality. Using the Gaussian Mixture Generative Model (GMGM), we provide a method to identify outliers and address this problem. Training on raw data is done using a VariationalAutoencoder (VAE). While avoiding rebuilding mistakes, we want to achieve as many brief features as possible. To predict the likelihood that examples contain many types of data, a dBN will utilise feature extractions and latent distributions in the future. The model's robustness is enhanced by enhancing the VAE, deep learning components, and the GMM overall. When densities surpass the training level, the Gaussian Mixture Model identifies outliers. To achieve this, it makes educated guesses about the densities of each data point. Compared to the deep learning Autoencoding Gaussian Mixture Model (dAGMM), GMGM achieves a 5.5 % higher area under the curve (AUC) on the OddS standard dataset. Experiments conducted on real datasets further demonstrate the efficacy of this strategy. © 2024

关键词： Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

An Optimized deep-learning-Based low Power Approximate Multiplier design

引用

computer Systems Science & engineering 2023年第2期44卷 1647-1657页

作者： M.Usharani B.Sakthivel S.Gayathri Priya T.Nagalakshmi J.Shirisha Department of Electronics and Communication Engineering Er.Perunal Manimekalai College of EngineeringKonneripalliHosur635117India Department of Electronics and Communication Engineering Pandian Saraswathi Yadav Engineering CollegeSivagangaiTamilnadu630561India Department of Electronics and Communication Engineering R.M.D Engineering CollegeGummidipundiTamilnadu601206India Department of Computer Science and Engineering Koneru Lakshmaiah Education FoundationVaddeswaramGuntur522502India Department of Electronics and Communication Engineering Malla Reddy Engineering CollegeHyderabadTelangana500015India

Approximate computing is a popularﬁeld for low power consumption that is used in several applications like image processing,video processing,multi-media and data *** Approximate computing is majorly performed with an arithmetic circuit particular with a *** multiplier is the most essen-tial element used for approximate computing where the power consumption is majorly based on its *** are several researchers are worked on the approximate multiplier for power reduction for a few decades,but the design of low power approximate multiplier is not so *** seems a bigger challenge for digital industries to design an approximate multiplier with low power and minimum error rate with higher *** overcome these issues,the digital circuits are applied to the deep learning(dl)approaches for higher *** recent times,dl is the method that is used for higher learning and prediction accuracy in severalﬁ***,the long Short-Term Memory(lSTM)is a popular time series dl method is used in this work for approximate *** provide an optimal solution,the lSTM is combined with a meta-heuristics Jel-lyﬁsh search optimisation technique to design an input aware deep learning-based approximate multiplier(dlAM).In this work,the jelly optimised lSTM model is used to enhance the error metrics performance of the Approximate *** optimal hyperparameters of the lSTM model are identiﬁed by jelly search ***ﬁne-tuning is used to obtain an optimal solution to perform an lSTM with higher *** proposed pre-trained lSTM model is used to generate approximate design libraries for the different truncation levels as a func-tion of area,delay,power and error *** experimental results on an 8-bit multiplier with an image processing application shows that the proposed approx-imate computing multiplier achieved a superior area and power reduction with very good results on error rates.

关键词： deep learning approximate multiplier lSTM jellyﬁsh

来源：评论

学校读者我要写书评

暂无评论

A Multi-tier accredit based security for trustworthiness in VANET's using broadcasting mechanism 2

A Multi-tier accredit based security for trustworthiness in ...

引用

2nd International Conference on Electrical, Electronics, Information and Communication Technologies, ICEEICT 2023

作者： Jyothi, N. Patil, Rekha H.K.E Society's S.L.N College of Engineering Department of Computer Science and Engineering Raichur India P. D. A. College of Engineering Department of Computer Science and Engineering Kalaburagi India

ISBN: (纸本)9798350397635

Vehicular Adhoc Networks (VANETs) have been more popular over the last decade. Vehicles now have sophisticated sensors that accomplish anything from automatically monitoring lanes to preventing front-end crashes to providing semi-autonomous driving to suggesting lane changes. Because of technological advancements, VANETs can now provide a broad range of useful services to drivers and passengers, including making the road trip more pleasant and safer. The data on traffic accidents and safety that is sent through an Adhoc network in a vehicle must be delivered unaltered. It is possible for hostile vehicles to hack into and intercept transmissions from vehicle Adhoc networks. Vehicle Adhoc networks can experience disruptions in both their performance and security. According to the research provided here, a three-tiered trust management system is a viable strategy for dealing with hostile vehicles in vehicle Adhoc networks. The proposed system begins with a trust rating for each vehicle in the Adhoc network, calculated from the vehicle's processing time, packet loss rate, and prior behaviour. Pick out certain vehicles to keep an eye on the flow of traffic around them so we know which ones can be trusted. The second-layer defenders are safe from malicious activity credits to past actions. The third layer of security safeguards the information needed to determine trustworthiness. Suggested method remains effective for verifying rogue VANET automobiles. When malevolent vehicles are added to a vehicle Adhoc network, data-packet transmitting rate increases, while source-to-destination latency decreases. © 2023 IEEE.

关键词： Vehicle transmissions

来源：评论

学校读者我要写书评

暂无评论

computer NETWORKS CYBER SECURITY VIA AN INTRUSION dETECTION SYSTEM

COMPUTER NETWORKS CYBER SECURITY VIA AN INTRUSION DETECTION ...

引用

2023 IEEE International Conference on Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication engineering, RMKMATE 2023

作者： latha, J. KarthickMurugan, S. logalakshmi, A. Department of Computer Science and Engineering R.M.K. Engineering College India Department of Computer Science and Engineering R.M.D. Engineering College India Department of Computer Science and Engineering Thiruthangal Nadar College India

ISBN: (纸本)9798350305708

Effectively identifying computer network attacks is still a challenge. This is due to recent attempts by cybercriminals to spoof intrusion detection systems (IdS) by altering packet contents. Additionally, the computer networks constantly add a large number of additional devices. Additionally posing a security risk to computer networks are these novel gadgets. To regulate computer network flows and offer security beforehand, you must do a thorough examination of the elements of your network, including the IdSs, the methodologies and devices used, particular kinds of attacks, and the tools that are used. This essay discusses intrusion detection methods, methodology, and tactics in addition to exploring innovative attack types, defenses, and current scientific study in the subject. © 2023 IEEE.

关键词： IdS methodologies IdS technologies IdS tools Intrusion detection system

来源：评论

学校读者我要写书评

暂无评论

Integrated normal discriminant analysis in mapreduce for diabetic chronic disease prediction using bivariant deep neural networks

引用

International Journal of Information Technology (Singapore) 2024年第8期16卷 4915-4929页

作者： Ramani, R. dhinakaran, d. Edwin Raja, S. Thiyagarajan, M. Selvaraj, d. Department of Computer Science and Engineering P.S.R Engineering College Sivakasi India Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R & amp D Institute of Science and Technology Chennai India Department of Electronics and Communication Engineering Panimalar Engineering College Chennai India

This study presents the Normal discriminant Feature Selection based Regressive deep Neural MapReduce (NdFS-RdNMR) framework designed for efficient prediction of diabetic chronic diseases using input datasets. The primary aim of NdFS-RdNMR is to enhance accuracy and recall in handling large datasets for chronic disease prediction. The framework integrates the Normal discriminative Preprocessing Model (NdPM) and bivariant regressive deep artificial neural network with MapReduce (BRdANNMR) classifier. Utilizing the Pima Indian diabetic dataset as input, NdFS-RdNMR conducts feature preprocessing through NdPM to extract relevant features for disease prediction. Non-traditional datasets are transformed into traditional formats via parameter rescaling to fit within predefined value ranges. Min–max normalization is applied to improve system accuracy while preserving data relationships. The BRdANNMR classifier utilizes bivariant regression analysis in the mapping phase to generate intermediary outcomes, which are then classified using a bipolar activation function in the reducer process. The framework achieves high accuracy and recall in early diabetes disease prediction, offering valuable insights for medical practitioners and researchers. © Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： Artificial neural network Classifier Feature selection MapReduce Normalization Regression analysis

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：