检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Recent Advances in Science and Engineering technology, ICRASET 2024

作者： Ghumman, Sukhman Praveena, J. Das, Sidhant Ballal, Suhas Kshirsagar, Pranali S. Gowtham, M.S. Chitkara University Centre of Research Impact and Outcome Punjab Rajpura140417 India Prince Shri Venkateshwara Padmavathy Engineering College Department of S&h Chennai127 India Chitkara University Chitkara Centre for Research and Development Himachal Pradesh 174103 India School of Sciences Chemistry and Biochemistry Karnataka Bangalore India Vishwakarma Institute of Technology Pune India Karpagam Institute of Technology Department of Electronics and Communication Engineering Coimbatore641105 India

ISBN: (纸本)9798350388602

Numerous cluster applications connect wireless sensor networks to the internet of things, and one of these steps is energy efficient clustering. Failure to account for clustering or heterogeneity makes evaluating a network's lifespan a difficult undertaking. Various techniques for energy-efficient clustering have been developed using models of the cluster head selection. Massive effort is required to model WSN-IoT full clustering. Part of the clusters system that is not discussed here is the stability phase and network lifespan. Clustering WSN-IoTs with an emphasis on heterogeneity and then scalability is the major goal of this study. Additionally, the presentation includes the specifics of the live metrics that are used for comparing the energy-efficient clustering methods across different time intervals. Prior to developing our first heterogeneous wide transmission distance protocol (HT-BTDP), we devote most of our attention to the selection of cluster heads. These results prove that the proposed HT-BTDP algorithm increases the stability period and lifespan in all analysed cases relative to SEP and EEHC. From the result, it can be observed that for the same vocabulary size the algorithm is on the higher side than SEP as well as EEHC. Further, in average the stability time is increased by 98.24% in the effectiveness time. While comparing with SEP, that is HIT, the efficacy is 59% and while comparing with TLE, that is LIT, the efficacy is 14%.84% when compared to EEHC. Also, to SEP, the average life span is 15 years. This makes it 77% longer, and compared to EEHC, it is 13. © 2024 IEEE.

关键词： Inductive power transmission

来源：评论

学校读者我要写书评

暂无评论

Application of Rodless Oil Production technology with Coiled Tubing Electric Submersible Pump in Jiyuan Oilfield 13th

Application of Rodless Oil Production Technology with Coiled...

引用

13th International Field Exploration and development Conference, IFEDC 2023

作者： Zhao, Yan-Hong Gao, Yu Gao, Hao Xiong, Li-Xin Chen, Xiang Research Institute of Xi’an Changqing Chemical Group Co. Ltd. CNPC Xi’an China Oil and Gas Technology Research Institute of Changqing Oilfield Company CNPC Xi’an China National Engineering Laboratory of Low Permeability Oil and Gas Field Exploratory and Development Xi’an China Oil Production Plant No. 3 of Changqing Oilfield CNPC Xi’an China

ISBN: (纸本)9789819702596

In view of the problems such as eccentric wear of pipe and rod and short pump inspection cycle in the application of rodless oil production technology in Jiyuan low permeability oilfield, 6 rodless oil production technology tests wells of coiled tubing electric submersible pump are carried out in G43 and G155 blocks. The comparison with the rod production process shows that the pump inspection period of the rod less oil production process is significantly extended, and the average pump inspection period of the four comparable oil wells is extended from 127 days to 219 days, which is still effective. The rodless oil production technology can effectively reduce the frequency of pump inspection, improve the production rate, and indirectly reduce the cost of wellbore maintenance and downhole operation. The daily power consumption of rodless oil production technology is greatly reduced, and the effect of energy saving is obvious. On average, 71.4KWh of electricity was saved per day for a single well, 428.6 KWh of electricity was saved per day for six wells in total, and 54000 yuan of electricity was saved in stages, which still kept stable operation. The rodless oil production technology of coiled tubing electric submersible pump occupies less land and is simple to install. Through optimization of the technology, the adaptability is improved and the application prospect in Jiyuan Oilfield is good. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Energy conservation

来源：评论

学校读者我要写书评

暂无评论

Enhanced Recognition of English Handwriting Styles Using a Hybrid CNN-Random Forest Model

Enhanced Recognition of English Handwriting Styles Using a H...

引用

Global Conference for Advancement in technology (GCAT)

作者： Rishabh Sharma Deepak Minhas Centre for Research Impact & Outcome Chitkara University Institute of Engineering and Technology Chitkara University Rajpura Punjab India Chitkara Centre for Research and Development Chitkara University Himachal Pradesh India

ISBN: (数字)9798350376685

ISBN: (纸本)9798350376692

Most organizations worldwide focus on handwriting recognition as it is vital in several assignments like the archive, education, and security. This is a research paper that puts forward handwriting type recognition employing CNNs and Random Forest classifiers. The study focuses on the recognition of four distinct English handwriting styles: There are four main styles which are; Italics, Spencerian Script, Palmer method, and Zaner-Bloser method. The preprocessing and data enhancement processes were carefully performed so that the model would have 1,000 samples for each of the two styles of handwriting. The hybrid model thus utilizes the CNN feature of extracting discriminative features from the handwriting samples, and the Random Forest classifier. The performance of the hybrid model was further assessed using measures such as; accuracy, logarithmic loss, MCC, and AUCROC. The results demonstrated that the hybrid CNN-Random Forest model outperformed standalone CNN and Random Forest models, achieving an accuracy of 91.2%, a logarithmic loss of 0.35, an MCC of 0.85, and an AUC-ROC of 0.92. Further validation of the said model and its efficiency was done by comparing epoch-wise as well as the batch size-wise results. Furthermore, the hybrid model was done in comparison with the other category of recognition known as handwriting recognition, and shown that the hybrid model has a greater performance.

关键词： Handwriting recognition Analytical models Accuracy Computational modeling Forestry Writing Feature extraction Loss measurement Convolutional neural networks Random forests

来源：评论

学校读者我要写书评

暂无评论

Efficient Trust Management for Blockchain-Enabled Smart City and Medical IoT with Eigenvector-Based ETMS 4

Efficient Trust Management for Blockchain-Enabled Smart City...

引用

4th IEEE International Conference on ICT in Business Industry and Government, ICTBIG 2024

作者： Katyal, Ashu Nalini Sunil, M. Tiwaskar, S.A. Karthikeyan, C. Arora, Mithhil Geetha, B. Chitkara University Chitkara Centre for Research and Development Himachal Pradesh 174103 India School of Mangement-PG Management Karnataka Bangalore India Vishwakarma Institute of Technology Pune India Karpagam Institute of Technology Department of Computer Science Engineering Coimbatore641105 India Chitkara University Centre of Research Impact and Outcome Punjab Rajpura140417 India Prince Shri Venkateshwara Padmavathy Engineering College Department of S&h Chennai127 India

ISBN: (纸本)9798331518981

Safe environment is aimed at creating within the context of Internet of Things (IoT) networks through the use of the Enhanced Trust Management System (ETMS) with the capability of detecting and eliminating the presence of malicious nodes and their contributions from the trust data. This is achieved using an eigenvector technique, which is integrated into a smart contract during the entire process. This allows edge nodes to invoke the contract at any time when it is necessary to invoke contract. To further enhance the security of the compiled trust information, the trust information is stored within a blockchain in blocks. As for routing the packets to the desired destinations, the result of the simulation demonstrates that ETMS is more effective than the systems currently in existence. In contrast to the systems that are currently in use, the suggested mechanism has a tool that will enable detection of contributions that have been faked in dispersed contexts and will therefore overcome a major deficiency. Moreover, the integration of ETMS into a number of circumstances that involve the Internet of Things, for example, Smart Cities, Medical IoT, and Industrial IoT, is entirely possible without any sort of complications. In the same regard, there is need to undertake further assessment on the capability of ETMS operating in real time across all these scenarios. © 2024 IEEE.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Optimizing Power Distribution Grids Using Particle Swarm Optimization Algorithm 4

Optimizing Power Distribution Grids Using Particle Swarm Opt...

引用

4th International Conference on Innovative Practices in technology and Management, ICIPTM 2024

作者： Kumar, Gaurav Sharma, Kuldeep Sharma, Kamal Dwivedi, Shashi Prakash Shrivastava, Anurag Bisht, Yashwant Singh Chitkara University Chitkara Centre for Research and Development Himachal Pradesh 174103 India Chitkara University Chitkara University Institute of Engineering and Technology Centre of Research Impact and Outreach Punjab Rajpura140401 India GLA University Department of Mechanical Engineering Mathura India Lloyd Institute of Engineering & Technology Greater Noida India Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Tamilnadu Chennai India Uttaranchal University Uttaranchal Institute of Technology Department of Mechanical Engineering Dehradun248007 India

ISBN: (纸本)9798350307757

This paper is the first to work on metaheuristic algorithm which combines PSO, GA, ACO and DE with deep learning to optimize power distribution networks. In particular, the interpretable methods including guided backscattering and GradCAM++. Valid tests were conducted on a realistic model of the electrical distribution network, which included various scenarios with loads and different conditions in the networks. The findings revealed that DE and PSO yielded superior results in terms of convergence rate, solution quality as well as reliability compared to other algorithms. Thanks to the oriented backpropagation and GradCAM++ techniques, one can get valuable information concerning how different network configurations affect optimization effects providing more transparency in solving a decision-making problem. With the contribution of DE in the comparative analysis with related works, this paper provides a broad view on optimization algorithms of electricity distribution network and enlarges its search scope. This study provides a profound understanding of the behaviour and performance of algorithms under distinct network conditions to informed professionals about tailored optimisation schemes. Introduction of interpretation techniques allows one to identify the opportunities for further enhancing transparency throughout hybrid approaches and optimization processes. © 2024 IEEE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Automated Cardiomegaly Detection from Chest X-rays Using InceptionV3: A Deep Learning Approach 4

Automated Cardiomegaly Detection from Chest X-rays Using Inc...

引用

4th International Conference on Power, Control and Computing Technologies, ICPC2T 2025

作者： Jain, Eshika Bhardwaj, Rishabh Centre for Research Impact & Outcome Chitkara University Institute of Engineering and Technology Chitkara University Punjab Rajpura140401 India Chitkara Centre for Research and Development Chitkara University Himachal Pradesh 174103 India

ISBN: (纸本)9798331530402

In this work, InceptionV3 is applied to identify cardiomegaly from chest X-ray images through a deep learning technique. The dataset, sourced from Kaggle, contains 5, 552 balanced images across two classes: The presence of cardiomegaly, coded as "True" and the absence of cardiomegaly coded as "False". Some pre-processing steps which include image resizing, normalization and augmentation improved the performance of the proposed model. The model was trained in 10 epochs with a batch size of 64 and produced an overall accuracy of 86%. The evaluation criteria such as precision, recall, F1-score, confusion matrix and classification report proved high and fair results on both classes. The results show a slight overfitting problem, which needs to be address in the future work by using approaches such as regularization and dropout. Future work includes using real and bigger datasets, combining different types of data, and using explainable AI for increased model interpretability. This work establishes the possibility of using deep learning for automating the identification of cardiomegaly, which can be an important direction for the development of efficient and accurate diagnostic tools in medical imaging. © 2025 IEEE.

关键词： Image coding

来源：评论

学校读者我要写书评

暂无评论

Numerical study of short-circuiting flow and particles in a gas cyclone

引用

Particuology 2023年第1期72卷 81-93页

作者： Sijie Dong Chenwen Wang Zihui Zhang Qinyu Cai Kejun Dong Teng Cheng Bo Wang Key Laboratory of Western China’s Environmental Systems of Ministry of Education Engineering Research Center of Fine Particle Pollution Control Technology and Equipment of Gansu ProvinceCollege of Earth and Environmental SciencesLanzhou UniversityLanzhou 730000China Key Laboratory of Resource Environment and Sustainable Development of Oasis of Gansu Province College of Geography and Environmental ScienceNorthwest Normal UniversityLanzhou 730000China Center for Infrastructure Engineering Western Sydney UniversityPenrithNSW 2751Australia

Short-circuiting flow is an important secondary flow in gas cyclones, which has a negative impact on the separation performance. To improve the understanding of the short-circuiting flow and guide the optimization of gas cyclones, this paper presents a numerical study of a cyclone using computational fluid dynamics. Based on the steady flow field, three methods were adopted to investigate the formation mechanism and characteristics of the short-circuiting flow and particles. The temporal variation of the tracer species concentration distribution reveals that the formation mechanism of the short-circuiting flow is the squeeze between the airflows entering the annular space of the gas cyclone at different times. The short-circuiting flow region, distinguished through the spatial distribution of the moments of age, is characterized by a small mean age and a large coefficient of variation. The proportion of the short-circuiting particles increases with the increase of the inlet velocity only for small particles. But with the increase of particle size, the proportion of the short-circuiting particles decreases faster at higher inlet velocities, resulting in significant differences in collection efficiency curves.

关键词： Gas cyclone Short-circuiting flow Computational fluid dynamics Species transport Moment of age Particle tracking

来源：评论

学校读者我要写书评

暂无评论

Bone Age Classification Using Deep Learning: A ResNet50 Model Approach 4

Bone Age Classification Using Deep Learning: A ResNet50 Mode...

引用

4th International Conference on Power, Control and Computing Technologies, ICPC2T 2025

作者： Kaushik, Pratham Khurana, Saniya Centre for Research Impact & Outcome Chitkara University Institute of Engineering and Technology Chitkara University Punjab Rajpura140401 India Chitkara Centre for Research and Development Chitkara University Himachal Pradesh 174103 India

ISBN: (纸本)9798331530402

The aim of this study was to create and assess a deep learning based automated Bone Age detection model using ResNet50 architecture. Bone age assessment is critical to diagnosing and treating pediatric conditions so our goal was to create a model that could accurately predict bone age from medical images. A transfer learning approach was used to use the pre trained ResNet50 model with a specific task of bone age classification, which was fine tuned. The dataset that was used was 12, 611 medical images and were grouped into 8 bone age groups. A confusion matrix was used to show accuracy, precision, recall, F1 score, etc. to evaluate the performance on the basis of different age groups and the model was trained and evaluated using standard classification metrics. On average, the model had 93.12% overall accuracy with very high precision, recall and F1 scores on most classes. The few misclassifications in the confusion matrix demonstrated strong generalization across age groups. This work shows that deep learning models, like ResNet50, can automate bone age assessment. The model performs exceptionally well, potentially making it suitable for use in clinical settings where it could help clinicians make faster, more accurate diagnoses. The results emphasise the utility of applying artificial intelligence in medical imaging for the development of future, more sophisticated, automated diagnostic techniques. © 2025 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Optimization of anchorage support parameters for soft rock tunnel based on displacement control theory

引用

Journal of Mountain Science 2023年第7期20卷 2076-2092页

作者： LI Gan MA Wei-bin YU Chang-yi TAO Zhi-gang WANG Feng-nian School of Civil&Environmental Engineering and Geography Science Rock mechanics Research InstituteNingbo UniversityNingbo 315000China Railway Engineering Research Institute China Academy of Railway Sciences Corporation LimitedBeijing 100081China CCCC First Harbor Engineering Company Co.Ltd.Tianjin 300461 CCCC-Tianjin Port Engineering Institute Co.Ltd.Tianjin 300222 State Key Laboratory for Geomechanics&Deep Underground Engineering Beijing 100083China Shanxi Transportation Technology Research and Development Co. LTDTaiyuan 030032China

In the construction of a soft rock tunnel,it is critical to accurately estimate the pre-stressed anchor support parameters for surrounding rock reinforcement;otherwise,engineering disasters may *** paper presents a support parameter selection method that aims to allow deformation as a control objective,which was applied to the tunnel located in Muzailing Highway,Min County,Dingxi City,Gansu Province,*** theoretical analysis,we have identified five factors that influence pre-stressing *** selection of mechanical parameters for the rock mass was carried out using an inverse analysis *** with the measured data,the maximum displacement error of the numerical simulation results was only 0.07 *** length of anchor cable,circumferential spacing of anchor cable,longitudinal spacing,and pre-stress index are adopted as the input parameters for the support vector machine neural network model based on particle swarm optimization(PSO-LSSVM).Besides,the vault subsidence and the maximum deformation of surrounding rock are considered as output values(performance indices).The goodness of fit between the predicted values and the simulated values exceeds ***,all support parameters within the acceptable deformation range are *** optimal support variables are derived by considering the construction cost and *** field application results show that it is feasible to construct the sample database utilizing the numerical simulation approach by taking the displacement as the control target and using the neural network to specify the appropriate support parameters.

关键词： Displacement control theory Anchorage support parameters Numerical simulation PSOLSSVM Tunnel construction

来源：评论

学校读者我要写书评

暂无评论

Understanding the Underlying Mechanics of Binary Brainwaves and Bayesian Framework 4

Understanding the Underlying Mechanics of Binary Brainwaves ...

引用

4th IEEE International Conference on ICT in Business Industry and Government, ICTBIG 2024

作者： Kannimuthu, S. Sohal, Jagmeet Rajarajeswari, S. Singla, Abhishek Asha, S. Mehta, Pradnya Karpagam College of Engineering Department of Information Technology Coimbatore641032 India Chitkara University Centre of Research Impact and Outcome Punjab Rajpura140417 India Prince Shri Venkateshwara Padmavathy Engineering College Department of S&h Chennai127 India Chitkara University Chitkara Centre for Research and Development Himachal Pradesh 174103 India School of Mangement - UG Management Karnataka Bangalore India Vishwakarma Institute of Technology Pune India

ISBN: (纸本)9798331518981

This work uses Bayesian reasoning, sophisticated optimization, and recurrent regularization to forecast and enhance brainwave signals for accuracy and resilience. The recommended approach examines brainwave waves using Bayesian reasoning. A Gaussian prior illustrates the initial concepts related to the hidden signal. Bayes' theorem calculates the posterior distribution, and MAP estimates discover the most probable hidden signal. We use backward samples in Markov Chain Monte Carlo (MCMC) to estimate the signal. We then validate this estimate using cross-validation and log-likelihood. Iterative regularization smoothes and denoises the signal while preserving significant characteristics and penalizing rapid changes. Gradient descent ensures smooth, accurate output during optimization. After extensive testing, the concept achieved 95.8% classification accuracy, 93.4% precision, 92.7% memory, and a 93.0% F1 score. A root mean square error of 0.04 and mean absolute error of 0.02 demonstrate its accuracy. Its rapid computing (12.5 seconds), scaling (9.5), noise resistance (9.8), and interpretability (9.0) make it successful. The findings demonstrate neurofeedback, brainwave analysis, and medical diagnostic applications for the proposed technique. They also define standards for signal processing accuracy, efficiency, and adaptability. © 2024 IEEE.

关键词： Mean square error

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：