检索结果-内蒙古大学图书馆

Apriori-roaring: frequent pattern mining method based on compressed bitmaps

International Journal of Business Intelligence and Data Mining 2022年第1期21卷 48-65页

作者： Colombo, Alexandre Spolon, Roberta Junior, Aleardo Manacero Lobato, Renata Spolon Cavenaghi, Marcos Antônio Computing Department São Paulo State University Bauru SP Brazil Department of Computer Science and Statistics São Paulo State University São José do Rio Preto SP Brazil Faculty of Business Humber Institute of Technology and Advanced Learning TorontoON Canada

Association rule mining is one of the most common tasks in data analysis. It has a descriptive feature used to discover patterns in sets of data. Most existing approaches to data analysis have a constraint related to execution time. However, as the size of datasets used in the analysis grows, memory usage tends to be the constraint instead, and this prevents these approaches from being used. This article presents a new method for data analysis called apriori-roaring. The apriori-roaring method is designed to identify frequent items with a focus on scalability. The implementation of this method employs compressed bitmap structures, which use less memory to store the original dataset and to calculate the support metric. The results show that apriori-roaring allows the identification of frequent elements with much lower memory usage and shorter execution time. In terms of scalability, our proposed approach outperforms the various traditional approaches available. Copyright © 2022 Inderscience Enterprises Ltd.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Recycled silicon solar cell-derived nanostructured p-black silicon device for high performance NO₂ gas sensor applications

RSC Applied Interfaces

引用

RSC Applied Interfaces 2024年第1期2卷 220-229页

作者： Aleem, Mahaboobbatcha Vishnuraj, Ramakrishnan Pullithadathil, Biji Nanosensors & Clean Energy Laboratory Department of Chemistry & Nanoscience and Technology PSG Institute of Advanced Studies Coimbatore 641 India Advanced Self-Powered Systems of Integrated Sensors and Technology Center Department of Electrical and Computer Engineering North Carolina State University Raleigh 27695 NC United States Center of Excellence in Advanced Materials and Green Technologies Amrita School of Engineering Coimbatore Amrita Vishwa Vidyapeetham India Department of Chemical Engineering and Materials Science Amrita School of Engineering Coimbatore Amrita Vishwa Vidyapeetham India

Nitrogen dioxide (NO2) is a toxic gas that can cause respiratory problems, and sensing its presence is crucial for environmental monitoring and industrial safety. This investigation presents a novel approach towards s...

Nitrogen dioxide (NO₂) is a toxic gas that can cause respiratory problems, and sensing its presence is crucial for environmental monitoring and industrial safety. This investigation presents a novel approach towards sensing NO₂ gas by utilizing partially completed/recycled silicon solar cells employing a metal-assisted etching process to fabricate a high-performance p-black-silicon based sensor. Structural and morphological analyses using X-ray diffraction patterns, Raman spectroscopy and cross sectional FESEM characterization confirm the integrity of the p-B-silicon sensor. By combining recycling techniques with advanced fabrication methods, the resulting sensor exhibits exceptional sensitivity, a low detection limit of 1 ppm, and rapid response times (12-14 s) when exposed to NO₂ gas concentrations ranging from 1 to 5 ppm. The enhanced sensitivity is attributed to the unique nanostructured comb-like morphology of the sensor material, which facilitates fast charge transport mechanisms, and a plausible sensing mechanism has been proposed and explained using a depletion model diagram and energy model diagram. This eco-friendly and cost-effective solution not only addresses electronic waste concerns but also highlights the potential of sustainable practices in scientific research. The findings emphasize on the importance of environmental consciousness and innovation, showcasing a promising future for gas sensing technology. By utilizing recycled materials and advanced fabrication techniques, this study contributes to the development of efficient, eco-friendly sensors for environmental monitoring applications, paving the way for a more sustainable and technologically advanced future in the field of gas sensors. © 2025 RSC.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sailfish Optimizer with Deep Transfer Learning-Enabled Arabic Handwriting Character Recognition

引用

computers, Materials & Continua 2023年第3期74卷 5467-5482页

作者： Mohammed Maray Badriyya B.Al-onazi Jaber S.Alzahrani Saeed Masoud Alshahrani Najm Alotaibi Sana Alazwari Mahmoud Othman Manar Ahmed Hamza Department of Information Systems College of Computer ScienceKing Khalid UniversityAbhaSaudi Arabia Department of Language Preparation Arabic Language Teaching InstitutePrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Industrial Engineering College of Engineering at AlqunfudahUmm Al-Qura UniversitySaudi Arabia Department of Computer Science College of Computing and Information TechnologyShaqra UniversityShaqraSaudi Arabia Prince Saud AlFaisal Institute for Diplomatic Studies RiyadhSaudi Arabia Department of Information Technology College of Computers and Information TechnologyTaif UniversityP.O.Box 11099Taif21944Saudi Arabia Department of Computer Science Faculty of Computers and Information TechnologyFuture University in EgyptNew Cairo11835Egypt Department of Computer and Self Development Preparatory Year DeanshipPrince Sattam bin Abdulaziz UniversityAlKharjSaudi Arabia

The recognition of the Arabic characters is a crucial task incomputer vision and Natural Language Processing fields. Some major complicationsin recognizing handwritten texts include distortion and patternvariabilities. So, the feature extraction process is a significant task in NLPmodels. If the features are automatically selected, it might result in theunavailability of adequate data for accurately forecasting the character ***, many features usually create difficulties due to high dimensionality *** this background, the current study develops a Sailfish Optimizer withDeep Transfer Learning-Enabled Arabic Handwriting Character Recognition(SFODTL-AHCR) model. The projected SFODTL-AHCR model primarilyfocuses on identifying the handwritten Arabic characters in the inputimage. The proposed SFODTL-AHCR model pre-processes the input imageby following the Histogram Equalization approach to attain this *** Inception with ResNet-v2 model examines the pre-processed image toproduce the feature vectors. The Deep Wavelet Neural Network (DWNN)model is utilized to recognize the handwritten Arabic characters. At last,the SFO algorithm is utilized for fine-tuning the parameters involved in theDWNNmodel to attain better performance. The performance of the proposedSFODTL-AHCR model was validated using a series of images. Extensivecomparative analyses were conducted. The proposed method achieved a maximum accuracy of 99.73%. The outcomes inferred the supremacy of theproposed SFODTL-AHCR model over other approaches.

关键词： Arabic language handwritten character recognition deep learning feature extraction hyperparameter tuning

来源：评论

学校读者我要写书评

暂无评论

Enhanced Community Identification Based on Spider Ant Colony Relative Feature Mining Algorithm Using Dense Net Convolutional Neural Network

Enhanced Community Identification Based on Spider Ant Colony...

引用

International Conference on computing and Networking Technology (ICCNT)

作者： A P Tharani S Poonguzhali Department of Computer Applications Vels Institute of Science Technology& Advanced Studies (VISTAS) Pallavaram Chennai Tamil Nadu India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Community detection is essential for identifying related groups in online social networks. Internet Communication Technology (ICT) makes e-learning and technology necessary in education. In addition, ICT plays an important role, from providing distance education and identifying interest groups to providing services to social interaction groups. Also, social realities, relative adversaries, groups to be served, etc., may be determined based on vested interests. Therefore, it is necessary to enable active researchers in social networks and identify communities to discover more, mainly behaviour-based groups. However, not any comment can be copied in terms of social associations. It is demonstrated that most machine learning algorithms using absolute mean ratios can derive interest scores based on social group organizations. However, these can reduce accuracy due to random correlations and lead to poor analysis. To solve this problem, we can implement deep learning-based social recognition and improve recognition accuracy. An improved community identification based on Spider Ant Colony Relative Feature Mining Algorithm (SACR-FMA) using Dense Net Convolution Neural Network (DNCNN) can be proposed. The online Community dataset is collected based on learner search features. The Learners Impact Behavioural Rate (LIBR) is initially estimated to find the learner’s interest. Then Edge Graph Semantic Subset Group Mining (EGSSGM) is used to marginalize the feature rate. Depending on the learner community rate, the Spider Ant Colony Relative Feature Mining Algorithm (SACR-FMA). The selected features are trained into Dense Net Layers (DNL) to create relative subgroup identity mining. Then the features are introduced into an optimistic Dense Net Convolution Neural Network (DNCNN) to identify the community interest class by category. The proposed method performs very well in detecting related subgroups in social networks compared to other systems. It provides accuracy, higher preci

关键词： Accuracy Social groups Convolution Image edge detection Neural networks Education Semantics Feature extraction Probabilistic logic Time complexity

来源：评论

学校读者我要写书评

暂无评论

Analysing various algorithms applied to Alzheimer’s disease dataset to help the Future Generation

Analysing various algorithms applied to Alzheimer’s disease...

引用

Intelligent and Innovative Technologies in computing, Electrical and Electronics (IITCEE), International Conference

作者： S. Athinarayanan K. Navaz Tamilselvi. P Shajeena J Vishwa Priya V M. Robinson Joel Department of CSE School of Computing Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Avadi Chennai Tamil Nadu India Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Avadi Chennai Department of Computer Science Vels Institute of Science Technology and Advanced Studies Chennai Department of CSE School of Computing Veltech Rangarajan Dr. Sakunthala R&D Institute of Science & Technology Department of Computer Science Vels Institute of Science Technology and Studies Chennai Department of Information Technology Kings Engineering College Chennai India

A sort of brain illness that affects the brain is Alzheimer's. Nowadays, older adults are more likely to have these ailments. People who have this illness have very poor memories and decreased memory. Additionally, their brain isn't working correctly. As a result, their regular practice is progressively beginning to decline. Alzheimer's is a kind of dementia for which there is no definitive treatment. This essay will help us learn more about Alzheimer's illness. We shall learn more about its causes, symptoms, and remedies. Additionally, we investigate several illness prediction methods employing Graph Neural Networks denoted as GNNs. Decision Tree, Random Forest algorithms, and more. However, the Random forest classifier gave good results with 86% accuracy and good recall values.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AI-Enhanced Healthcare: Densenet Based Alzheimer's Disease Prediction and Online Consultation for Accessible Medical Support 2

AI-Enhanced Healthcare: Densenet Based Alzheimer's Disease P...

引用

2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025

作者： Wilfred Blessing, N.R. Gunasekaran, Hemalatha Hariharan, B. Al Jabri, Jaber Saleh Salim Kavitha, S.J. Sutherlin Subitha, G. College of Computing and Information Sciences University of Technology and Applied Sciences Ibri Oman SRM Institute of Science and Technology Kattankulathur Department of Computational Intelligence Tamil Nadu India Vels Institute of Science Technology and Advanced Studies Department of Computer Science and Engineering Chennai India Stella Mary's College of Engineering Department of Computer Science and Engineering Tamil Nadu Aruthenganvilai India

ISBN: (纸本)9798331505745

Improvements in patient care and early disease detection possibilities are two of the ways artificial intelligence is transforming the healthcare industry. Alzheimer's disease, a neurodegenerative disease that worsens with time, is among the most difficult diseases to exactly identify in early stages. Patients thus delay in treatment and experience a decline in their quality of life. Research is still under progress, thus knowledge about how AI-driven prediction models could be combined with readily available healthcare services remains lacking. This work presents a special artificial intelligence-powered system consisting of DenseNet-based deep learning for Alzheimer's disease prediction with an online consultation platform. The proposed approach analyzes brain MRI data and classifies Alzheimer's stages with higher accuracy using a DenseNet architecture, well-known for its exceptional performance in the field of feature extraction. Comprising three thousand magnetic resonance imaging (MRI) images, the dataset has been preprocessed for noise reduction and tuned for models performance. At 98.5%, the DenseNet model exceeded other methods including VGGNet and ResNet in accuracy. © 2025 IEEE.

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

Deep-Readout Random Recurrent Neural Networks for Real-World Temporal Data

引用

SN computer science 2022年第3期3卷 222页

作者： Evanusa, Matthew Shrestha, Snehesh Patil, Vaishnavi Fermüller, Cornelia Girvan, Michelle Aloimonos, Yiannis Department of Computer Science University of Maryland College Park MD United States Department of Physics University of Maryland College Park MD United States Institute for Advanced Computer Studies University of Maryland College Park MD United States

Echo State Networks (ESN) are a class of recurrent neural networks that can learn to regress on or classify sequential data by keeping the recurrent component random and training only on a set of readout weights, which is of interest to the current edge computing and neuromorphic community. However, they have struggled to perform well with regression and classification tasks and therefore, could not compete in performance with traditional RNNs, such as LSTM and GRU networks. To address this limitation, we have developed a novel hybrid network, called Parallelized Deep Readout Echo State Network (PDR-ESN) that combines the deep learning readout with a fast random recurrent component, with multiple ESNs computing in parallel. We show the PDR-ESN architecture allows for different configurations of the sub-reservoirs, leading to different variants which we explore. Our findings suggest that different variants of the PDR-ESN offer various advantages in different task domains, with some performing better in regression and others in classification. In all cases, our PDR-ESN architecture outperforms the corresponding gradient-based LSTM and GRU architectures in terms of training time as well as accuracy. To further evaluate, we also compared against a Transformer encoder classifier, where the PDR-ESN outperformed on all tasks. We conclude that our proposed network demonstrates a good trade-off between the fast training times of traditional ESNs with the accuracy of deep backpropagation for real-world tasks. We hope that this architecture offers an alternative approach to sequential processing for edge computing as well as more biologically-realistic network development. © 2022, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Deep learning Hybrid neural networks Recurrent neural network Reservoir computing Time series analysis

来源：评论

学校读者我要写书评

暂无评论

The Role of Exploratory Data Analysis and Pre-processing in the Machine Learning Predictive Model for Heart Disease

The Role of Exploratory Data Analysis and Pre-processing in ...

引用

Advances in computing, Communication and Applied Informatics (ACCAI), International Conference on

作者： K. Mahalakshmi P. Sujatha School of Computing Sciences Vels Institute of Science Technology & Advanced Studies Chennai India Women’s Christian College Chennai Department of Information Technology Vels Institute of Science Technology & Advanced Studies Chennai

The heart is the organ which pumps blood to the human body. There is an important need for early disease prediction systems for heart related problems. The disease prediction system supports the doctors to diagnose critical diseases as early as possible. The disease prediction system is built using field knowledge of the healthcare profession and machine learning (ML), artificial intelligence. This research paper aims to explore the role of Exploratory Data Analysis [EDA] and pre-processing of heart disease (HD) data for the prediction of HD. This research explores three ML classifiers, namely Random Forest (RF), Support Vector Machine (SVM) and Decision Tree (DT) with missing value imputers, feature scaling techniques, data analytics, and visualization tools using four benchmark HD datasets from the UCI repository. Imputation methods mean, median, most frequent, constant, KNN imputer and iterative imputer with scaling of features were analysed with the help of three classifiers RF, SVM and DT. Random Forest with an iterative imputer achieved 86.41% of accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Map Building of Indoor Environment with Sensors using Neural Network

Map Building of Indoor Environment with Sensors using Neural...

引用

2023 Winter Summit on Smart computing and Networks, WiSSCoN 2023

作者： Latha Mary, S Angel Ulagapriya, K. Poonguzhali, A. Menaha, R. David, Beaulah Priyadharshini, T.R. Sri Eshwar College of Engineering Department of Computer Science and Business Systems Coimbatore India Vels Institute of Science Technology and Advanced Studies Department of Computer Science and Engineering Chennai India Sri Sairam College of Engineering Department of Electronics and Communication Engineering Bangalore India Sri Eshwar College of Engineering Department of Information Technology Coimbatore India Hindusthan College of Engineering and Technology Department of Information Technology Coimbatore India

ISBN: (纸本)9798350334050

The necessity of a blueprint of a building structure is a mandatory requirement for any reconnaissance or rescue operations. In our project, we build a modular system combining sensors related to sonar, laser, micro-wave to read sensory values and generate a 2D path of any building. The data is fetched and stored to feed to anOptimal Neural Network (ONN)-based computing system to create a 2D route with minimal discrepancies of error. Here the NN architecture is fine-tuned using Modified Dolphin Partner Optimization (MDPO) Exploration of unknown environments and space using autonomous vehicles has recently gained good attention in the field of Robotic Mapping. The recent advancements in the Internet of Things have enabled us to establish an ideal frame of reference for sonar and lidar-based systems. New effects are displayed by the sensors according to the physical characteristics of a room. The range data from sensors in various surroundings are interpreted by NNs. The distorted errors due to the material medium, particles, and moving objects present in the environment pose a threat to building a high-quality path map. The sensor fusion technique is applied to the rotatable modular array sensor to minimalize discrepancies caused by cloth materials during sonar readings, particle noise in an environment for Lidar reading, and moving human bodies present in the environment for path building and obstacle detection. © 2023 IEEE.

关键词： Optical radar

来源：评论

学校读者我要写书评

暂无评论

Cloud-Powered Neural Networks for Sustainable Fishing Practices and Stock Management System 4

Cloud-Powered Neural Networks for Sustainable Fishing Practi...

引用

4th International Conference on Sustainable Expert Systems, ICSES 2024

作者： Suresh, M. Xavier Prathik, A. Arun, V. Venugopal, R. Ganeshbabu, T.R. Muthulekshmi, M. School of Advanced Sciences and Languages Vit Bhopal University Department of Physics Madhya Pradesh Bhopal India Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Tamil Nadu Chennai India School of Computing Srm Institute of Science and Technology Faculty of Engineering and Technology Department of Computing Technologies Kattankulathur Tamil Nadu Chennai India Department of Mathematics Tamil Nadu Salem India Department of Electronics and Communication Tamil Nadu Namakkal India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Department of Biomedical Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798331540364

Sustainable fishing methods and efficient stock management are crucial considering growing environmental concerns;fishing practices and effective stock management are imperative. This research presents a novel approach that uses neural networks (NN) hosted in the cloud to transform sustainable fishing and stock management. This method trains NN to make predictions by combining several data sources, such as satellite images, weather patterns, and catch records. These models can reliably predict fish stocks' dynamics, giving stakeholders the information needed to make informed decisions. Crucial for real-time processing and storage of massive information is the scalability and flexibility offered by cloud infrastructure. This framework provides the appropriate usage of resources while simultaneously optimizing fishing tactics, which helps protect marine ecosystems. It demonstrates that method promotes sustainable fishing via thorough case studies and simulations. It provides a flexible and scalable solution to the problems confronting marine biodiversity and the fishing industry by combining advanced technology with ecological principles. To ensure a more egalitarian and sustainable future for fisheries management on a global scale, method is a giant leap forward in balancing commercial interests with environmental protection. Integrating data, ensuring sensors are accurate, managing huge datasets, managing regulatory compliance, and encouraging stakeholders to work together for sustainable practices are all challenges. © 2024 IEEE.

关键词： Fisheries

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：