检索结果-内蒙古大学图书馆

Perspective of Generalizing deep Boltzmann Machine for ECG Signal Classification

NATIONAL ACADEMY SCIENCE LETTERS-INDIA 2025年第1期48卷 39-43页

作者： Jeyaraj, Pandia Rajan Asokan, Siva Prakash Kathiresan, Aravind Chellachi Nadar, Edward Rajan Samuel Mepco Schlenk Engn Coll Autonomous Dept Elect & Elect Engn Sivakasi India

deep learning is a highly efficient technique for handling large volume big data and decision-making processes. The above objective is achieved by incorporating healthcare service provider knowledge as a rule to meticulously classify physiological signal like Electrocardiogram (ECG) signal from the extracted large amount of big data from the wearable sensor. In this study, we generalized a novel deep Boltzmann machine (DBM) to diagnose arrhythmia in real-time ECG signals. The performance of proposed DBM was evaluated by accuracy, specificity, sensitivity and mean field interference of training algorithms. From the obtained results, we claim that the proposed deep learning model has high performance in the classification of most of the arrhythmia ECG and has high accuracy of 96.8% and sensitivity of 98.83% in classification. Moreover, the significance of proposed DBM model performs consistently on various real-time ECG dataset.

关键词： Data analysis deep learning algorithm deep Boltzmann machine ECG signal Wearable devices

来源：评论

学校读者我要写书评

暂无评论

RLIS: Resource Limited Improved Security Beyond Fifth-Generation Networks Using deep learning algorithms

IEEE OPEN JOURNAL OF THE COMMUNICATIONS SOCIETY

引用

IEEE OPEN JOURNAL OF THE COMMUNICATIONS SOCIETY 2023年 4卷 2383-2396页

作者： Selvarajan, Shitharth Manoharan, Hariprasath Khadidos, Alaa O. Shankar, Achyut Mekala, M. S. Khadidos, Adil O. Kebri Dehar Univ Dept Comp Sci Kebri Dehar Ethiopia Leeds Beckett Univ Sch Built Environm Engn & Comp Leeds LS1 3HE England Panimalar Engn Coll Dept Elect & Commun Engn Chennai 600123 India King Abdulaziz Univ Fac Comp & Informat Technol Dept Informat Syst Jeddah 23436 Saudi Arabia King Abdulaziz Univ Ctr Res Excellence Artificial Intelligence & Data Jeddah 23436 Saudi Arabia Univ Warwick Secure Cyber Syst Res Grp SCSRG WMG Coventry CV4 7AL England Lovely Profess Univ Sch Comp Sci Engn Phagwara 144411 India Robert Gordon Univ Sch Comp Aberdeen AB10 7AQ Scotland King Abdulaziz Univ Fac Comp & Informat Technol Dept Informat Technol Jeddah 23436 Saudi Arabia

This study explores the feasibility of allocating finite resources beyond fifth generation networks for extended reality applications through the implementation of enhanced security measures via offloading analysis (RLIS). The quantification of resources is facilitated through the utilization of parameters, namely energy, capacity, and power, which are equipped with proximity constraints. These constraints are then integrated with activation functions in both multilayer perceptron and long short term memory models. Furthermore, the system model has been developed using vision-based computing, which involves managing data queues in terms of waiting periods to minimize congestion for data transmission with limited resources. The major significance of the proposed method is to utilize allocated spectrums for future generation networks by allocating necessary resources and therefore high usage of resources by all users can be avoided. In addition the advantage of the proposed method is secure the networks that operate beyond 5G where more number of users will try to share the allocated resources that needs to be provided with high security conditions.

关键词： deep learning algorithm extended reality applications fifth generation networks limited resource visual systems

来源：评论

学校读者我要写书评

暂无评论

Predicting first session working alliances using deep learning algorithms: A proof-of-concept study for personalized psychotherapy

引用

PSYCHOTHERAPY RESEARCH 2022年第8期32卷 1100-1109页

作者： Zhou, Ying Chen, Xiao-yu Liu, Ding Pan, Yu-lin Hou, Yan-fei Gao, Ting-ting Peng, Fei Wang, Xiao-cong Zhang, Xiao-yuan Southern Med Univ Sch Publ Hlth Dept Psychol 1023 South Shatai Rd Guangzhou 510515 Guangdong Peoples R China Shenzhen Univ Coll Psychol Shenzhen Peoples R China South China Univ Technol Sch Comp Sci & Engn Guangzhou Peoples R China Southern Med Univ Sch Nursing Dept Humanities & Mental Nursing Guangzhou Peoples R China Southern Med Univ Zhujiang Hosp Dept Psychiat Guangzhou Peoples R China Southern Med Univ Nanfang Hosp Dept Obstet & Gynaecol 1023 South Shatai Rd Guangzhou 510515 Guangdong Peoples R China

Objective The aim of this proof-of-concept study is to develop a predictive model based on deep learning algorithms to predict working alliances after the first therapeutic session and to provide a basis for clinical decisions. Methods Using a sample of 325 patients and 32 psychotherapists from three university counseling centers, a deep learning algorithm known as fully connected neural networks (FCNNs) was adopted to construct data-driven predictive models. The performance differences between the model including only patient indicators and the model including both patient and therapist indicators were compared. The optimal model was further tested in a general hospital sample of 85 patients and 8 therapists. Results The model incorporating both patient indicators and therapist-level indicators (R-2: 0.30 +/- 0.02) performed better than the model incorporating only patient indicators (R-2: 0.11 +/- 0.02). The performance of this model decreased when being transferred to the independent general hospital sample, but still retained some predictive value (R-2 = 0.11). Conclusion This study showed that the inclusion of therapist-level indicators can improve the performance of a predictive model in predicting working alliances. This model could assist clinical decisions on choosing psychotherapists for patients and may also initiate new possibilities for future research.

关键词： personalized psychotherapy clinical decision supports deep learning algorithm working alliance therapist-level indicators

来源：评论

学校读者我要写书评

暂无评论

Traditional Ceramic Manufacturing Process Optimization Method Based on Cloud Computing and deep learning algorithms 24

Traditional Ceramic Manufacturing Process Optimization Metho...

引用

4th International Conference on Internet of Things and Machine learning

作者： Yang, Shiyu Liu, Dazhi Dankook Univ Yongin South Korea Xiamen Acad Arts & Design Xiamen Peoples R China Fuzhou Univ Fuzhou Peoples R China

ISBN: (纸本)9798400710353

In order to improve the quality of the products and the efficiency of production, the traditional process for making ceramics has some limit on cost, yield, and a product conformity rate, so the traditional process needs to be optimized. In this paper, the performance of various optimization methods such as CNN, RNN, and traditional process were empirically compared in ceramic fabrication processes. By conducting the conformity test 20 times, the conformity of product, cost, and yield was evaluated. The experimental results show the proposed optimization techniques using CNN and RNN significantly improved ceramic fabrication processes with respect to the traditional process. The CNN-based method further achieved the highest pass rate, with rates ranging from 97.1% to 98.9%, followed by the RNN-based method from 96.6%, to 98.5%, and the traditional-based method from 94.7% to 95.9%. Thus, it is suggested that deep learning algorithms may have the potential to improve the conformity of products and reduce costs in manufacturing ceramic products.

关键词： Ceramic Making Process Cloud Computing deep learning algorithm Loss Function

来源：评论

学校读者我要写书评

暂无评论

A novel combined model based on advanced optimization algorithm, and deep learning model for abnormal wind speed identification and reconstruction

引用

ENERGY 2024年 312卷

作者： Zhu, Anfeng Zhao, Qiancheng Shi, Zhaoyao Yang, Tianlong Zhou, Ling Zeng, Bing Hunan Univ Sci & Technol Engn Res Ctr Hunan Prov Min & Utilizat Wind Turbin Xiangtan 411201 Peoples R China Beijing Univ Technol Beijing Engn Res Ctr Precis Measurement Technol & Beijing 100124 Peoples R China XEMC Wind Power Co Ltd Xiangtan 411102 Peoples R China

When the state of the sensors of the wind turbine, especially the anemometer, is abnormal, it will affect the correctness of other parameters of the whole power system. To recognize and reconstruct the abnormal data accurately and efficiently, this study proposes an improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN), extreme learning machine (ELM), crazy improve butterfly optimization algorithm (CIBOA), and bi-directional long short-term memory (BILSTM). In this system, the ICEEMDAN is utilized to decompose the original wind speed sequence, and then the ELM is employed as the initial prediction engine to extract the features of each sub-sequence to achieve the preliminary prediction outcomes. The CIBOA is employed to optimize the BILSTM model parameters. To further explore the unsteady features in the wind speed series, the residual results of the preliminary prediction are modeled using BILSTM, and the predicted residuals and preliminary results are integrated to obtain the final reconstructed values. In addition, the combined model is discussed in detail employing six assessment indicators, improvements of the reconstruction model, DieboldMariano test, operation time, and sensitivity analysis. The results indicate that the Pearson correlation coefficient (PCC) values of the proposed model are 0.9986, 0.9978, and 0.9979, respectively. It is concluded that the proposed hybrid reconstruction model accurately identifies and reconstructs abnormal wind speed, which provides a new technique for the reasonable utilization of wind energy.

关键词： Wind speed reconstruction deep learning algorithm Improved optimization algorithms Combination strategy

来源：评论

学校读者我要写书评

暂无评论

Online measurement and segmentation algorithm of coarse aggregate based on deep learning and experimental comparison

引用

CONSTRUCTION AND BUILDING MATERIALS 2022年第0期327卷 127033-127033页

作者： Hu, Xiang Fang, Huaiying Yang, Jianhong Fan, Lulu Lin, Wenhua Li, Jiantao Huaqiao Univ Coll Mech Engn & Automat Xiamen 361021 Fujian Peoples R China Shenzhen Municipal Engn Corp Shenzhen Peoples R China

The quality of image processing affects the results of aggregate particle size detection. So far, the aggregate image segmentation is still limited to the traditional watershed algorithm (WA) and threshold segmentation algorithm, and their segmentation effect is limited. Therefore, a deep learning algorithm (DLA) to segment stacked coarse aggregate images was presented in this paper. Then it was used to segment the images of aggregates with different aggregate materials, particle sizes and mixing ratios, and the segmentation results were analyzed. The dataset required was made by the labelme, and trained to obtain the segmentation model of the DLA. The test results were compared with that of the traditional WA. For single-stage aggregates with particle sizes of 5-10 mm, 10-20 mm and 20-31.5 mm, the proportion of cumulative gradation calculated by DLA was increased by 5.93%, 28.62% and 23.62%, respectively, for different base materials of coarse aggregate, the proportion of cumulative gradation calculated by DLA was increased by 28.62%, 37.68% and 12.78%, respectively. For aggregate images with different mixing ratios, the segmentation results of DLA were closer to the actually configured gradation. The experimental results showed that the DLA could avoid the common phenomenon of over-segmentation and under-segmentation in the WA, and had general applicability in segmenting coarse aggregates with different particle sizes and aggregate materials.

关键词： Stacked coarse aggregate Image processing deep learning algorithm Watershed algorithm Online measurement

来源：评论

学校读者我要写书评

暂无评论

A Convolutional Neural Network Using Anterior Segment Photos for Infectious Keratitis Identification

引用

CLINICAL OPHTHALMOLOGY 2025年 19卷 73-81页

作者： Satitpitakul, Vannarut Puangsricharern, Apiwit Yuktiratna, Surachet Jaisarn, Yossapon Sangsao, Keeratika Puangsricharern, Vilavun Kasetsuwan, Ngamjit Reinprayoon, Usanee Kittipibul, Thanachaporn Chulalongkorn Univ Fac Med Ctr Excellence Cornea & Stem Cell Transplantat Dept Ophthalmol Bangkok Thailand King Chulalongkorn Mem Hosp Excellence Ctr Cornea & Stem Cell Transplantat Dept Ophthalmol Thai Red Cross Soc Bangkok Thailand IM Impower Co Ltd Bangkok Thailand Chulalongkorn Univ Fac Med Bangkok Thailand

Purpose: To develop a comprehensively deep learning algorithm to differentiate between bacterial keratitis, fungal keratitis, noninfectious corneal lesions, and normal corneas. Methods: This retrospective study collected slit-lamp photos of patients with bacterial keratitis, fungal keratitis, non-infectious corneal lesions, and normal cornea. Causative organisms of infectious keratitis were identified by either positive culture or clinical response to single treatment. Convolutional neural networks (ResNet50, DenseNet121, VGG19) and Ensemble with probability weighting were used to develop a deep learning algorithm. The performance including accuracy, precision, recall, F1 score, specificity and AUC has been reported. Results: Total of 6478 photos from 2171 eyes, composed of 2400 bacterial keratitis, 1616 fungal keratitis, 1545 non-infectious corneal lesions, and 917 normal corneas were collected from hospital database. DenseNet121 demonstrated the best performance among three convolutional neural networks with the accuracy of 0.8 (95% CI 0.74-0.86). The ensemble technique showed higher performance than single algorithm with the accuracy of 0.83 (95% 0.78-0.88). Conclusion: Convolutional neural networks with ensemble techniques provided the best performance in discriminating bacterial keratitis, fungal keratitis, non-infectious corneal lesions, and normal corneas. Our models can be used as a screening tool for nonophthalmic health care providers and ophthalmologists for rapid provisional diagnosis of infectious keratitis.

关键词： infectious keratitis cornea ulcer keratitis conventional neural network deep learning algorithm

来源：评论

学校读者我要写书评

暂无评论

N2 injection to enhance gas drainage in low-permeability coal seam: A field test and the application of deep learning algorithms

引用

ENERGY 2024年 290卷

作者： Wang, Kai Gong, Haoran Wang, Gongda Yang, Xin Xue, Haiteng Du, Feng Wang, Zhie China Univ Min & Technol Beijing Beijing Key Lab Precise Min Intergrown Energy & Re Beijing 100083 Peoples R China China Univ Min & Technol Beijing Sch Emergency Management & Safety Engn Beijing 100083 Peoples R China Univ Sci & Technol Beijing Sch Civil & Resources Engn Beijing 100083 Peoples R China Capital Univ Econ & Business Sch Management Engn Beijing 100083 Peoples R China

N2 injection to enhance coal seam gas drainage is an effective technology for coalbed methane recovery. Nevertheless, there is a limited body of research addressing the application of ECBM technology for gas management in low permeability coal seams within underground coal mines, and the effect is uncertain. Additionally, numerical simulators have been challenged to accurately predict methane emissions during gas injection and replacement. In this study, firstly, an underground field trials of N2 injection replacement in a coal mine with low -permeability coal seams in China were conducted, and a comparative analysis of "N2 injection to enhance gas drainage" and "conventional drainage" technique was performed. The result show that injecting pressurized N2 into a low -permeability coal seam could increase the pressure gradient to promote the directional flow of free gas from the coal seam cracks to the gas -production boreholes. After N2 injection, the mixed flow rate and CH4 flow rate significantly increased. Additionally, the gas content in the coal seam in the experimental area significantly decreased. Secondly, the lag -effect was discussed. Upon discontinuation of N2 injection, the gasproducing mixed flow initially increased slightly, then gradually decreased, and eventually settled at a high level. Despite the attenuation of N2 injection volume, the CH4 flow rate continued to increase during intermittent injection and remained high after gas injection discontinuation. Finally, three deep learning algorithms (BP, LSTM, and TCN) were employed to predict the dynamic change of gas drainage in coal seams displaced by N2 injection, based on the results of the field test. The results indicated that deep learning algorithms exhibited superior prediction performance. The TCN model demonstrated the lowest approximation error rate, displaying optimal performance in predicting the CH4 flow rate during nitrogen injection for enhanced gas drainage. Additionally, it exhibited

关键词： deep learning algorithm Model optimization Underground displacement by injecting N2 N2 injection to enhance gas drainage

来源：评论

学校读者我要写书评

暂无评论

Predicting lake water quality index with sensitivity-uncertainty analysis using deep learning algorithms

引用

JOURNAL OF CLEANER PRODUCTION 2023年第1期406卷

作者： Talukdar, Swapan Shahfahad, Shakeel Ahmed, Shakeel Naikoo, Mohd Waseem Rahman, Atiqur Mallik, Santanu Ningthoujam, Sudhakar Bera, Somnath Ramana, G. V. Jamia Millia Islamia Fac Nat Sci Dept Geog New Delhi 110025 India Natl Inst Technol Dept Civil Engn Agaratala Tripura India Maulana Azad Natl Urdu Univ MANUU Sch Sci Hyderabad 500032 India Cent Univ South Bihar Dept Geog Gaya 824236 Bihar India Indian Inst Technol Delhi Dept Civil Engn New Delhi 110016 India

Regular monitoring and assessment of water quality is essential to maintain the quality of lake water. A commonly used method for assessing water quality is the Water Quality Index (WQI). Artificial intelligence (AI) can predict the WQI rapidly and more accurately than conventional methods. In this study, a stacking ensemble model based on deep learning (DL) was proposed to predict the WQI by integrating three models: Gradient Boosting Machine (GBM), Generalized Linear Model (GLM) and Neural Network (NN). The performance of this model was compared with that of deep Dense Neural Network (DNN) and Convolutional Neural Network (CNN). The inclusion of a DNN model, which was used for the first time in water pollution research to perform sensitivity and uncertainty analysis in predicting WQI, added a new dimension to the workflow. The mean square error (MSE), mean absolute error (MAE), root mean square error (RMSE) and correlation coefficient (R2) were used to evaluate the performance of the WQI prediction models. The results showed that the WQI of the water samples ranged from 90.75 to 145.29, indicating poor to very poor water quality. The validation results showed that the stack model was superior to all other models in terms of prediction accuracy, with MSE of 25.77, RMSE of 5.07, MAE of 3.5 and R2 of 0.98. The DNN-based sensitivity analysis showed that pH and turbidity significantly affect the WQI and should be monitored to minimise water pollution. The uncertainty analysis indicated that electrical conductivity and total dissolved solids have the highest uncertainty in predicting WQI. This study provides researchers, decision makers and water scientists with accurate information on water quality and enables the implementation of clean production processes to reduce pollution and improve water quality.

关键词： Lake water quality deep learning algorithm Convolutional neural network Sensitivity analysis Uncertainty analysis Loktak lake

来源：评论

学校读者我要写书评

暂无评论

A Combined Landslide Displacement Prediction Model Based on Variational Mode Decomposition and deep learning algorithms

引用

WATER 2024年第23期16卷 3503页

作者： Sun, Mengcheng Guo, Yuxue Huang, Ke Yan, Long Powerchina Huadong Engn Corp Ltd Hangzhou 311122 Peoples R China Zhejiang Univ Inst Water Sci & Engn Coll Civil Engn & Architecture Hangzhou 310058 Peoples R China Hohai Univ Res Inst Geotech Engn Nanjing 210098 Peoples R China

Accurate landslide displacement prediction is an essential prerequisite for early warning systems aimed at mitigating geological hazards. However, the inherent nonlinearity and dynamic complexity of landslide evolution often hinder forecasting performance. Previous studies have frequently combined signal decomposition techniques with individual machine learning methods to enhance prediction reliability. To address the limitations and uncertainties associated with individual models, this study presents a hybrid framework for displacement forecasting that combines variational mode decomposition (VMD) with multiple deep learning (DL) methods, including long short-term memory neural network (LSTM), gated recurrent unit neural network (GRU), and convolutional neural network (CNN), using a cloud model-based weighted strategy. Specifically, VMD decomposes cumulative displacement data into trend, periodic, and random components, thereby reducing the non-stationarity of raw data. Separate DL networks are trained to predict each component, and the forecasts are subsequently integrated through the cloud model-based combination strategy with optimally assigned weights. The proposed approach underwent thorough validation utilizing field monitoring data from the Baishuihe landslide in the Three Gorges Reservoir (TGR) region of China. Experimental results demonstrate the framework's capacity to effectively leverage the strengths of individual forecasting methods, achieving RMSE, MAPE, and R values of 12.63 mm, 0.46%, and 0.987 at site ZG118, and 20.50 mm, 0.52%, and 0.990 at site XD01, respectively. This combined approach substantially enhances prediction accuracy for landslides exhibiting step-like behavior.

关键词： Baishuihe landslide displacement prediction deep learning algorithm weighted combination strategy

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：