检索结果-内蒙古大学图书馆

IEEE Region 10 Symposium

作者： Nikita Gupta Kuldeep Singh Jadon Preeti Soni Nitin Gupta Sanjay Kumar Dhurandher Department of Computer Science & Engineering NIT Hamirpur (HP) India Department of Information Technology Netaji Subhas University of Technology New Delhi National Institute of Electronics and Information Technology New Delhi India

ISBN: (数字)9798350364866

ISBN: (纸本)9798350364873

Heart disease prediction is a critical aspect of modern healthcare and demands accurate and efficient models for timely diagnosis. Machine learning models in heart disease prediction analyze patient data, with cross-validation ensuring reliable performance, aiding model selection, and optimizing parameters for enhanced accuracy. The k value in cross-validation determines the number of folds into which the dataset is divided for training and validation. In the proposed work, optimization of the k-value in cross-validation is done using Particle Swarm Optimization (PSO), which is utilized to improve the evaluation of the predictive accuracy of various models. PSO dynamically adjusts the k-value, balancing computational efficiency with accurate model evaluation. The result shows that among various ML models, Random Forest, with an 86.95% mean accuracy, emerges as the preferred choice, offering reliable predictions for improved diagnostics.

关键词： Heart Training Analytical models Accuracy Computational modeling Predictive models Data models Reliability Optimization Diseases

来源：评论

学校读者我要写书评

暂无评论

Ontology-driven sentiment analysis in indian healthcare sector 8th

Ontology-driven sentiment analysis in indian healthcare sect...

引用

8th International Conference on Frontiers of Intelligent Computing: Theory and Applications, FICTA 2020

作者： Sharma, Abhilasha Chandra Singh, Anmol Pandey, Harsh Srivastava, Milind Department of Computer Science & Engineering Delhi Technological University Delhi42 India Netaji Subhas Institute Of Technology Delhi78 India

ISBN: (纸本)9789811556784

In today’s world, social media platforms have emerged as one of the most prominent media for expressing opinions. Sentiment analysis for utilizing the big data socially available over the web has become one of the most researched areas. Sentimental analysis is used to get the public perception over any event, topic or subject matter by classifying data into various polarity categories like positive, neutral, negative, etc. Various computational techniques such as machine learning and deep learning are used to perform polarity analysis and to find the best classifiers. Traditional techniques tend to create feature vectors in order to quantify the data, but these feature vectors are often very large for tweets collected over a particular domain and that leads to a performance reduction. This paper proposes a combined approach which utilizes domain ontology with machine learning methods in order to reduce the size of feature vector to increase the performance for all machine learning models. The observations state that our technique provides a significant advantage over the traditional methods. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2021.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Federated Learning Empowered Routing for Opportunistic Network Environments

Federated Learning Empowered Routing for Opportunistic Netwo...

引用

IEEE International Conference on Communications Workshops, ICC

作者： Jagdeep Singh Sanjay Kumar Dhurandher Isaac Woungang Department of Computer Science and Engineering Sant Longowal Institute of Engineering and Technology Longowal Punjab India Department of Information Technology Netaji Subhas University of Technology New Delhi India National Institute of Electronics and Information Technology New Delhi India Department of Computer Science Toronto Metropolitan University Toronto ON Canada

ISBN: (数字)9798350304053

ISBN: (纸本)9798350304060

Opportunistic network systems (OppNets), a subclass of Delay-tolerant networks (DTNs) systems, are a category of wireless networks designed for operation in demanding and constantly changing environments, where traditional network infrastructure is often unreliable, constrained, or absent. These adverse network conditions make conventional routing algorithms impractical. This paper proposes a Federated Learning-based Router (FLRouter) suitable for use in Opportunistic network environments, which harnesses the capabilities of federated learning. In this framework, the nodes opportunistically select the next-hop relay for message forwarding based on the real-time network state and nodes' local knowledge. The contribution of this work is the seamless integration of federated learning algorithms into opportunistic network systems, allowing for optimal routing decisions. Through simulations and in-depth analysis, the effectiveness of our approach in achieving efficient routing within OppNets is demonstrated.

关键词： Training Federated learning Conferences Wireless networks Scalability Routing Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Interaction of children with an augmented reality smartphone app

引用

International Journal of Information technology (Singapore) 2020年第3期12卷 711-716页

作者： Yadav, Savita Chakraborty, Pinaki Kochar, Gurtej Ansari, Deeheem Division of Computer Engineering Netaji Subhas University of Technology New Delhi 110078 India

Many children now get access to smartphones by two years of age and gradually learn to operate them. The objective of this study was to determine the age at which children become capable of using smartphone apps with augmented reality. We developed an augmented reality smartphone app in C# and studied the interaction of 60 children aged between two and eight years with it. We conducted a preference test to determine the interest of the children in using the app and a proficiency test to determine the ability of the children to use the app. We observed that 5% children aged two and three years, 25% children aged four to six years, and 55% children aged seven and eight years were interested in playing with the app. The children below the age of seven years were overwhelmed by the interplay of real and virtual objects displayed on the screen, and did not prefer playing with the app. Alternatively, the seven and eight year old children were able to use the app and were enthusiastic about it. However, the seven and eight year old children required 39.78% more time to use the app when compared with a similar app without augmented reality. We concluded that children develop skills necessary to use augmented reality software by the age of seven years. We recommend that augmented reality be used in educational apps for children aged seven years and more to enhance their learning experience. © 2020, Bharati Vidyapeeth's institute of computer Applications and Management.

关键词： Augmented reality Child educational app Human–computer interaction Smartphone

来源：评论

学校读者我要写书评

暂无评论

Systematic study of the(n,2n)reaction cross section for^(121)Sb and^(123)Sb isotopes

引用

Chinese Physics C 2022年第5期46卷 77-94页

作者： R.K.Singh N.L.Singh R.D.Chauhan Mayur Mehta S.V.Suryanarayana Rajnikant Makwana B.K.Nayak H.Naik Tarak Nath Nag K.Katovsky Department of Physics Faculty of Sciencethe M.S.University of BarodaVadodara-390002INDIA Department of Physics Netaji Subhas University of TechnologyDwarkaNew Delhi-110078INDIA Institute for Plasma Research Gandhinagar-382428INDIA Nuclear Physics Division Bhabha Atomic Research CentreMumbaiINDIA Radiochemistry Division Bhabha Atomic Research CentreMumbaiINDIA Department of Electrical Power Engineering Brno University of TechnologyBrno-61600Czech Republic

The cross sections of the^(121)Sb(n,2n)^(120)Sb^(m) and ^(123)Sb(n,2n)^(122)Sb reactions were measured at 12.50,15.79 and 18.87 MeV neutron energies relative to the standard ^(27)Al(n,α)^(24)Na monitor reaction using neutron activation and offline γ-ray *** of the samples was performed at the BARC-TIFR Pelletron Linac Facility,Mumbai,*** quasi-monoenergetic neutrons were generated via the ^(7)Li(p,n)*** model calculations were performed by nuclear reaction codes TALYS(ver.1.9)and EMPIRE(ver.3.2.2)using various input parameters and nuclear level density *** cross sections of the ground and the isomeric state as well as the isomeric cross section ratio were studied theoretically from reaction threshold to 26 MeV *** effect of pre-equilibrium emission is also discussed in detail using different theoretical *** present measured cross sections were discussed and compared with the reported experimental data and evaluation data of the JEFF-3.3,ENDF/B-VIII.0,JENDL/AD-2017 and TENDL-2019 libraries.A detailed analysis of the uncertainties in the measured cross section data was performed using the covariance analysis ***,a systematic study of the(n,2n)reaction cross section for^(121)Sb and^(123)Sb isotopes was also performed within 14-15 MeV neutron energies using various systematic *** work helps to overcome discrepancies in Sb data and illustrate a better understanding of pre-equilibrium emission in the(n,2n)reaction channel.

关键词： antimony (n,2n)reaction cross section 7Li(p,n)reaction neutron source neutron activation and offlineγ-ray spectrometry systematic formulae covariance analysis TALYS(ver.1.9)and EMPIRE(ver.3.2.2)codes

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning Based Congestion Control Mechanism for Opportunistic Networks

Reinforcement Learning Based Congestion Control Mechanism fo...

引用

2022 IEEE GLOBECOM Workshops, GC Wkshps 2022

作者： Singh, Jagdeep Dhurandher, Sanjay Kumar Woungang, Isaac Chatzimisios, Periklis Rodrigues, Joel J. P. C. Sant Longowal Institute of Engineering and Technology Department of Computer Science and Engineering Punjab Longowal India Netaji Subhas University of Technology Department of Information Technology New Delhi India Ryerson University Department of Computer Science TorontoON Canada International Hellenic University Thessaloniki Greece College of Computer Science and Technology Qingdao China Instituto de Telecomunicações Covilhã6201-001 Portugal

ISBN: (纸本)9781665459754

This work proposes a Reinforcement Learning-based Congestion Control protocol (called (RLCC)) for Opportunistic Networks to find the optimal number of message counts based on the real-time density in the network. (RLCC) jointly uses Q-learning and fuzzy logic to make the routing decision based on real attributes such as social status, centrality, activeness, message lifetime, hop count, and battery status. In the proposed (RLCC) scheme, the message priority is required to maintain the optimal count of messages in the network, and the fuzzy inference rules perform well in predicting the best hop for message transmission. All network nodes get inputs from the environment and take action accordingly. If the message is transferred successfully to the intended node, then the node receives the reward for the action, otherwise, the penalty will be assigned. Based on this, network nodes only select those nodes, which are capable to transmit the message from one node to another node. Simulation results demonstrate that RLCC is superior to the MARLCC and F-GSAF routing protocols using the infocom2006 real mobility data trace, in terms of delivery probability, latency, and overhead ratio. © 2022 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Drought prediction using artificial neural network 2

Drought prediction using artificial neural network

引用

2nd International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2022

作者： Metta, Pardha Saradhi Chintamaneni, Anish Kumar, Ashish Yadav, Jatin Kumar, Vishesh Bhaskar, Bharath Vellore Institute of Technology Department of Computer Science and Engineering Tamil Nadu Vellore India Karunya Institute of Technology and Sciences Department of Computer Science and Engineering Tamil Nadu Coimbatore India Netaji Subhas University of Technology Dwarka Department of Information Technology Delhi India Karunya Institute of Technology and Sciences Department of Instrumentation and Technology Tamil Nadu Coimbatore India SRM Institute of Science and Technology Department of Computer Science and Engineering Tamil Nadu Kattankulathur India Pes University Department of Electronics and Communications Karnataka Bangalore India

ISBN: (纸本)9781665437899

Drought has been one of the most frightening natural calamity that is being faced by the humans., and it is generally faced by the farmers all around the world. It can occur anywhere in the world and is also known as one of the slow disaster as it stays for a very longer time period and maybe even more if it wants to be harsher. Drought not only impacts the human life but also the agriculture, world economies and energy that had been infiltrated by the farmers. Everything goes on stakes during this calamity and the basic needs such as food are not easy to get during these times and the inflammation is at peak due to supply and demand instability. There are many ways which can be done to avoid the drought, which include drip irrigation to save water during the times of drought, rainwater harvesting can also be a saviour, crop engineering, desalination of water and many more things. The main solution for this would be to analyse the weather and the future outcomes of it which would help in preparing for the worse situation and also the soil prediction can help a lot when it comes to predicting this situation. The paper aims to take the data of weather and soil together to predict how droughts can be avoided. Deep learning techniques will help to get a great idea if the drought is going to happen or not. © 2022 IEEE.

关键词： Drought

来源：评论

学校读者我要写书评

暂无评论

Reliability and Availability Analysis of Degrading Systems Under Imperfect Repair Scenario 2nd

Reliability and Availability Analysis of Degrading Systems U...

引用

2nd International Conference on Recent Advances in Mechanical engineering, RAME 2020

作者： Kumar, Varun Kumar, Girish Soni, Umang Division of Manufacturing Processes and Automation Engineering Netaji Subhas Institute of Technology Delhi India Department of Mechanical Production & Industrial and Automobile Engineering Delhi Technological University Delhi India

ISBN: (纸本)9789811596773

In this work, mathematical models are developed for a degrading system to assess system performance. Reliability and availability are considered to be measures of system performance. Generally, mechanical systems deteriorate gradually before they fail catastrophically. So, it would be more appropriate, if multi-state degradation is considered in the modelling and to take appropriate maintenance action upon failure of the system. The Markov approach is employed for modelling and analysis of degrading system as it can incorporate repair and other dependency features in the model. The proposed technique is demonstrated for a two-stage reciprocating air compressor system. The novelty of the paper is a specific computational approach for reliability and availability assessment of degrading systems. © 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Availability Imperfect repair Opportunistic maintenance Reliability Stochastic Markov process

来源：评论

学校读者我要写书评

暂无评论

Classification of Parkinson's Disease using CNN and ANN with the aid of Drawing and Acoustic Feature 2

Classification of Parkinson's Disease using CNN and ANN with...

引用

2nd International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2022

作者： Fiza, Syed Kumar, Ashish Yadav, Jatin Reddy, Sainandan Sidda, Tej Kurma Sai, Kaarthik Dayananda Sagar College of Engineering Department of Medical Electronics Karnataka Bengaluru India Delhi Technological University Department of Information Technology Shabad Daulatpur Delhi India Netaji Subhas University of Technology Department of Instrumentation and Technology Dwarka Delhi India Indian Institute of Technology Department of Civil Engineering Hyderabad India Gandhi Institute of Technology and Management Department of Computer Science and Engineering Andhra Pradesh Vishakhapatnam India Data Analytics Vellore Institute of Technology Department of Computer Science and Engineering Andhra Pradesh Amaravati India

ISBN: (纸本)9781665437899

Parkinson's disease manifests itself in a variety of ways. slurred speech, muscle rigidity, and tremors. The condition can also affect the production of the brain's dopamine. Therapies can help treat conditions after a diagnosis, however, there is no remedy. The paper primarily analyses the many drawing evaluation methods and disease diagnoses that have been used. The AI deep learning idea was used, along with convolutional neural networks and artificial neural networks. However, this article proposes a model for detecting disease using drawings of different persons from two classes. Disease detection on photos has been accomplished using a variety of techniques such as data augmentation, sequential, and CNN. The acoustic feature data was processed using a Decision tree and ANN with GridsearchCV, and the overall accuracy on testing data was 98 percent. © 2022 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Question Independent Automated Code Analysis and Grading using Bag of Words and Machine Learning

Question Independent Automated Code Analysis and Grading usi...

引用

2019 International Conference on Computing, Power and Communication Technologies, GUCON 2019

作者： Rai, Kaushal Kumar Gupta, Bhavya Shokeen, Pardeep Chakraborty, Pinaki Netaji Subhas University of Technology Division of Computer Engineering New Delhi India

ISBN: (纸本)9789353510985

Our first-hand experience with the recruiting process of companies helped us realize that existing systems judge coding responses solely on the basis of test cases passed and often additional manual involvement is needed to determine the quality of code. We aim to build an open source code base to automatically grade coding responses. This work will help save the tedious effort on the part of Subject Matter Experts (SMEs) by proving useful for grading responses in MOOCs (Massive Open Online Courses) as well as coding rounds in the recruitment process. We have built our work on foundations introduced in extant research in the area. We have achieved better precision (89%) in addition to better Pearson Correlation Coefficient (0.981) as compared to existing methods using the bag of words technique to calculate the distance vector. Various machine learning models were explored to achieve optimal results. These results and observations provide a promise of successful application of this technique in other areas requiring automated grading. © 2019 Galgotias University.

关键词： Support vector machines

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：