检索结果-内蒙古大学图书馆

2022 International Conference on Machine Learning and Data engineering, ICMLDE 2022

作者： Ashwin Valliappan, S. Ramya, G.R. Department of Computer Science and Engineering Amrita School of Computing Coimbatore Amrita Vishwa Vidyapeetham India

Modern deep learning algorithms have achieved tremendous success in many visual applications by training a model with all relevant task-specific data. In this module fake reviews evolving in online political and property data will be discussed. Regarding political information there are many differences while switching from offline to online mode. The views and comments of the politicians in social media act as a question mark "whether it is true or not?". In some cases, it appears to be real and sometimes it may be a false/fake statement. All because, the online information is often considered as the most important source of info for the users these kinds of reviews and comments affects the trust factors of social media. Now days in social media, more of toxic contents and unwanted information were present rather than the useful information. These toxic comments acts as a threat for users using the application. Hence users do not come forward to post their thoughts and actions or to share the information. This module is used to distinguish reviews, identify the factor in online mode of political and property comments in social media. The LSTM and BERT (Bidirectional Encoder Representations from Transformers) algorithms are used in the first module because they offer a wide variety of parameters such as learning rates, input and output biases, and text categorization. Additionally, GPT2 (Generative Pre-Trained Transformer 2) is implemented which helps in text generation, increasing the size of dataset for training in different classification models. Thus it is important to understand for us that ultimately the model will be getting trained in such a way that it is able to give accurate results while we are undergoing classification of text and also while we are undergoing the identification of fake/authentic comments that are there in the source of our data. © 2023 The Authors. Published by Elsevier B.V.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Energy-Aware and Relay Relocation Routing Protocol for Sink Based Wireless Sensor Networks 2

Energy-Aware and Relay Relocation Routing Protocol for Sink ...

引用

2nd International Conference on Edge computing and Applications, ICECAA 2023

作者： Raghav, R.S. Prabu, U. Thirugnansambandam, Kalaipriyan School of Computing Sastra Deemed University Thanjavur India Velagapudi Ramakrishna Siddhartha Engineering College Department of Cse Vijayawada India School of Computer Science and Engineering Vit University Chennai Campus Chennai India

ISBN: (纸本)9798350347579

Wireless Sensor Networks (WSNs) refers to networks of spatially dispersed sensors which can communicate to a central location by forwarding data collected through monitoring of physical conditions. The process of finding a suitable path to destination from source is called routing. IOT devices utilize the service of WSN. Power consumption is the main aspect to be noticed because sensor node battery replacement is impossible. An algorithm, which is cluster based with choosing of cluster head can stable the connections. In this paper, it represents an energy aware clustering using energy-aware routing and relay relocation protocol. This protocol uses relay nodes to relieve the excessive power consumption of the cluster heads. The data transmission range is adjusted by initializing the maximum energy lifetime of the overall network. Thus, it improves the overall network performance in terms of increase in throughput, packet delivery ratio and decrease in delay value. Also, comparison with the existing Delay-aware Green Routing Protocol (DGRP) with our proposed protocol in the matter of throughput, average residual energy, number of packets sent to the base station using Matlab/Simulink. © 2023 IEEE.

关键词： Simulink

来源：评论

学校读者我要写书评

暂无评论

Machine learning-based classification of rock discontinuity trace:SMOTE oversampling integrated with GBT ensemble learning

引用

International Journal of Mining science and Technology 2022年第2期32卷 309-322页

作者： Jiayao Chen Hongwei Huang Anthony G.Cohn Dongming Zhang Mingliang Zhou Key Laboratory of Geotechnical and Underground Engineering of Ministry of Education Department of Geotechnical EngineeringTongji UniversityShanghai 200092China School of Computing University of LeedsLS29JT LeedsUnited Kingdom Department of Computer Science and Technology Tongji UniversityShanghai 211985China School of Civil Engineering Shandong UniversityJinan 250061China Luzhong Institute of Safety Environmental Protection Engineering and MaterialsQingdao University of Science and TechnologyZibo 255000China School of Mechanical and Electrical Engineering Qingdao University of Science and TechnologyQingdao 260061China

This paper presents a hybrid ensemble classifier combined synthetic minority oversampling technique(SMOTE),random search(RS)hyper-parameters optimization algorithm and gradient boosting tree(GBT)to achieve efficient and accurate rock trace identification.A thirteen-dimensional database consisting of basic,vector,and discontinuity features is established from image *** data points are classified as either‘‘trace”or‘‘non-trace”to divide the ultimate results into candidate trace *** is found that the SMOTE technology can effectively improve classification performance by recommending an optimized imbalance ratio of 1:5 to 1:***,sixteen classifiers generated from four basic machine learning(ML)models are applied for performance *** results reveal that the proposed RS-SMOTE-GBT classifier outperforms the other fifteen hybrid ML algorithms for both trace and nontrace ***,discussions on feature importance,generalization ability and classification error are conducted for the proposed *** experimental results indicate that more critical features affecting the trace classification are primarily from the discontinuity ***,cleaning up the sedimentary pumice and reducing the area of fractured rock contribute to improving the overall classification *** proposed method provides a new alternative approach for the identification of 3D rock trace.

关键词： Tunnel face Rock discontinuity trace Machine learning Gradient boosting tree Generalization ability

来源：评论

学校读者我要写书评

暂无评论

Water Quality Monitoring in Eel Aquaculture Using IoT

Water Quality Monitoring in Eel Aquaculture Using IoT

引用

IEEE UP Section Conference on Electrical Computer and Electronics (UPCON)

作者： Thangam S. Gurupriya M Pooja Damavarapu Kavinya Mahesh Monesh Harsha Vardhan Department of Computer Science and Engineering Amrita School of Computing Bengaluru India

ISBN: (数字)9798350378726

ISBN: (纸本)9798350378733

In eel aquaculture it is crucial to manage water quality to support the growth, health and longevity of the stock. This study focuses on overseeing indicators such, as temperature, turbidity and water levels in eel farming setups using IoT technology. By incorporating these sensors it becomes simpler to gather and analyze real time data facilitating interventions and precise adjustments to uphold water conditions. The objective is to enhance understanding of the changing water quality factors in eel farming environments and develop strategies for risk prevention and proactive control. The ultimate aim is to boost productivity, efficiency and environmental responsibility, in eel farming practices through the application of sensor technologies.

关键词： Temperature sensors Smart agriculture Temperature Turbidity Real-time systems Internet of Things Sustainable development Intelligent sensors Aquaculture Farming

来源：评论

学校读者我要写书评

暂无评论

5G Data Offloading Using Fuzzification with Grasshopper Optimization Technique

引用

Computer Systems science & engineering 2022年第7期42卷 289-301页

作者： V.R.Balaji T.Kalavathi J.Vellingiri N.Rajkumar Venkat Prasad Padhy Department of ECE Sri Krishna College of Engineering and TechnologyCoimbatore641008India Department of EIE Kongu Engineering CollegeErode638060India School of Information Technology and Engineering Vellore Institute of TechnologyVellore632014India Department of CSE School of EngineeringPresidency UniversityBangalore560064India School of Computing Science and Engineering VIT Bhopal UniversityBhopal466114India

Data ofﬂoading at the network with less time and reduced energy con-sumption are highly important for every *** applications process the data very quickly with less power *** technology grows towards 5G communication architecture,identifying a solution for QoS in 5G through energy-efﬁcient computing is *** this proposed model,we perform data ofﬂoading at 5G using the fuzziﬁcation *** IoT devices create tasks in the network and are ofﬂoaded in the cloud or mobile edge nodes based on energy *** base stations,small(SB)and macro(MB)stations,are initialized and theﬁrst tasks randomly ***,the tasks are pro-cessed using a fuzziﬁcation algorithm to select SB or MB in the central *** optimization is performed using a grasshopper algorithm for improving the QoS of the 5G *** result is compared with existing algorithms and indi-cates that the proposed system improves the performance of the system with a cost of 44.64 J for computing 250 benchmark tasks.

关键词： 5G energy consumption task ofﬂoading fuzziﬁcation grasshopper optimization QoS mobile IoT

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Based ADMET Prediction in Drug Discovery 4

Machine Learning Based ADMET Prediction in Drug Discovery

引用

4th IEEE Global Conference for Advancement in Technology, GCAT 2023

作者： Bhavitha Lekshmi Prasad, P.S. Ani, R. Deepa, O.S. Department of Computer Science and Applications Amrita School of Computing Amrita Vishwa Vidyapeetham Amritapuri India Department of Mathematics Amrita School of Engineering Amrita Vishwa Vidyapeetham coimbatore India

ISBN: (纸本)9798350305258

A drug is a substance or compound with the ability to treat or prevent disease in people or animals. Drug discovery is the process of identifying prospective medications for certain ailments, and it can take several years to accomplish. However, the introduction of machine learning has simplified the procedure. Virtual screening's major goal is to minimize the virtual compound space of biological molecules. To do this, we developed the VIRTUAL SCREENING TOOL, a virtual molecular descriptor calculator that can analyze molecules and assess their drug-likeness based on specific rules. We used Django with PyCharm, a Python IDE, to create a molecular description calculator, fingerprint generator, and prediction interface. The tool begins by inputting SMILES, which is the chemical structure of the molecule, and outputs molecular descriptors, which are the properties of the molecules, including their physicochemical properties, absorption, distribution, metabolism, lipophilicity, excretion, toxicity, drug-likeness rules, and fingerprint generation. The outputs are available in CSV format for download. © 2023 IEEE.

关键词： Drug Fingerprint Physiochemical property Prediction SMILES

来源：评论

学校读者我要写书评

暂无评论

Natural Question Generation using Transformers and Reinforcement Learning 20

Natural Question Generation using Transformers and Reinforce...

引用

20th OITS International Conference on Information Technology, OCIT 2022

作者： Biswas, Dipshikha Nadipalli, Suneel Sneha, B. Gupta, Deepa Amudha, J. Department of Computer Science and Engineering Amrita School of Computing Bengaluru Amrita Vishwa Vidyapeetham India

ISBN: (纸本)9781665493482

Natural Question Generation (NQG) is among the most popular open research problems in Natural Language Processing (NLP) alongside Neural Machine Translation, Open Domain Chatbots, etc. Among the many approaches taken up to solve this problem, neural networks have been deemed the benchmark in this particular research area. This paper aims at adopting a generator - evaluator framework in a neural network architecture to allow additional focus on the context of the content used for framing a question. The generator uses NLP architectures like transformers (T5) to generate a question given a context while the evaluator uses Reinforcement Learning (RL) to check the correctness of the generated question. The involvement of RL has improved the results (as shown in Table 2), and there is increased computational efficiency as the training is coupled with the policy of RL. This turns the problem into a reinforcement learning task and allows for the generation of a wide range of questions for the same context-answer pair. The given algorithm is tested on the benchmark dataset - SQuAD with BLEU score as the evaluation metric © 2022 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Finite Element Variational Multiscale Method for Stationary Incompressible Magnetohydrodynamics Equations

引用

Advances in Applied Mathematics and Mechanics 2023年第5期15卷 1142-1165页

作者： Huayi Huang Yunqing Huang Qili Tang Hunan Key Laboratory for Computation and Simulation in Science and Engineering Key Laboratory of IntelligentComputing&Information Processing of Ministry of EducationSchool of Mathematics and Computational ScienceXiangtan UniversityXiangtanHunan 411105China

In this paper,we propose a variational multiscale method(VMM)for the stationary incompressible magnetohydrodynamics *** method is defined by large-scale spaces for the velocity field and the magnetic field,which aims to solve flows at high Reynolds *** provide a new VMM formulation and prove its stability and ***,some numerical experiments are presented to indicate the optimal convergence of our method.

关键词： Variational multiscale method stationary incompressible magnetohydrodynamics large-scale spaces stability and convergence high Reynolds numbers

来源：评论

学校读者我要写书评

暂无评论

Optimize a novel Integrated Solutions to analyses Privacy persevering of the Internet of Things 6

Optimize a novel Integrated Solutions to analyses Privacy pe...

引用

6th International Conference on Information Systems and Computer Networks, ISCON 2023

作者： Mishra, Amit Kumar Tripathi, Neha Bagla, Piyush Pandey, Neeraj Kumar Mittal, Saksham Rana, Deepak Singh Graphic Era Hill University Dept. of Computer Science and Engineering Uttarakhand Dehradun India Graphic Era Deemed to Be University Dept. of Computer Science and Engineering Uttarakhand Dehradun India National Institute of Technology Computer Science and Engineering Dept. Punjab Jalandhar India Dit University School of Computing Uttarakhand Dehradun India Graphic Era Hill University School of Computing Uttarakhand Dehradun India

ISBN: (纸本)9798350346961

Internet of Things (IoT) develops a global network of interconnected items or things that will play a significant part in Future Internet (FI). For the IoT to be extensively accepted by individuals and businesses, there must be confidence in the IoT security architecture. It is crucial to establish how IoT devices may connect and share data with one other and with remote servers in an efficient and safe manner. Therefore, we provide solutions for IoT environment security and privacy in this paper. Our study begins with the construction of novel three layered approach with Pseudo-Random Number Generators. That after, we have applied a Key Generation Center (KGC) protocol to enable secure multicast group communication in the IoT. A key setup method that ensures the secrecy, authenticity, and integrity of data shared in the network while taking into account the features of IoT devices is one of the IoT security basics. To evaluate the performance of the proposed system, we examine its computational and communication costs.. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Chi-Square and PCA Based Feature Selection for Diabetes Detection with Ensemble Classifier

引用

Intelligent Automation & Soft computing 2023年第5期36卷 1931-1949页

作者： Vaibhav Rupapara Furqan Rustam Abid Ishaq Ernesto Lee Imran Ashraf School of Computing and Information Sciences Florida International UniversityUSA Department of Computer Science Khwaja Fareed University of Engineering and Information TechnologyRahim Yar Khan64200Pakistan Department of Computer Science Broward CollegeBroward CountyFloridaUSA Department of Information and Communication Engineering Yeungnam UniversityGyeongsan-si38541Korea

Diabetes mellitus is a metabolic disease that is ranked among the top 10 causes of death by the world health *** the last few years,an alarming increase is observed worldwide with a 70%rise in the disease since 2000 and an 80%rise in male *** untreated,it results in complications of many vital organs of the human body which may lead to *** detection of diabetes is a task of signiﬁcant importance to start timely *** study introduces a methodology for the classiﬁcation of diabetic and normal people using an ensemble machine learning model and feature fusion of Chi-square and principal component *** ensemble model,logistic tree classiﬁer(LTC),is proposed which incorporates logistic regression and extra tree classiﬁer through a soft voting *** are also performed using several well-known machine learning algorithms to analyze their performance including logistic regression,extra tree classiﬁer,AdaBoost,Gaussian naive Bayes,decision tree,random forest,and k nearest *** addition,several experiments are carried out using principal component analysis(PCA)and Chi-square(Chi-2)fea-tures to analyze the inﬂuence of feature selection on the performance of machine learning classiﬁ*** indicate that Chi-2 features show high performance than both PCA features and original ***,the highest accuracy is obtained when the proposed ensemble model LTC is used with the proposed fea-ture fusion framework-work which achieves a 0.85 accuracy score which is the highest of the available approaches for diabetes *** addition,the statis-tical T-test proves the statistical signiﬁcance of the proposed approach over other approaches.

关键词： Diabetes mellitus prediction feature fusion ensemble classiﬁer principal component analysis chi-square

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：