Research on Pneumothorax Classification Model of DenseNet Based on Multilayer Network Optimization by Hongliang Huang, Qike Wang, Lidong Wang

“…This method optimizes multiple network layers and ensures the convergence of the neural network by reducing the learning rate with each iteration. …”
Get full text

Emotional State Analysis Model of Humanoid Robot in Human-Computer Interaction Process by Boxin Peng

“…In view of the shortcomings of traditional methods, this study designed an emotion analysis model based on deep neural network to detect the emotion of interactive objects and built an open-domain dialogue system of humanoid robot. …”
Get full text

Research on Human Motion Recognition Based on Data Redundancy Technology by Hong-Lan Yang, Meng-Zhe Huang, Zheng-Qun Cai

“…Then, the depth feature of processed image is extracted by depth motion map; finally, feature recognition is carried out by convolution neural network so as to achieve the purpose of human action recognition. …”
Get full text

Combined Diagnosis of PD Based on the Multidimensional Parameters by Mohammad Heidari

“…Diagnose signals are found with the method based on information fusion and semisupervised learning for HFC PD, adaptive mutation parameters of particle entropy for ultrasonic signals, and IIA-ART2A neural network for UHF signals. In addition, integrate the diagnostic results, which are the probability of fault of various defects and matrix, of different PD diagnosis signals, and analysis with Sugeno fuzzy integral to get the final diagnosis.…”
Get full text

Multi-user physical layer authentication mechanism based on lightweight CNN and channel feature assistance by Yankun WANG, Dengke GUO, Dongtang MA, Jun XIONG, Xiaoying ZHANG

“…To address the problems of poor robustness and high complexity of current physical layer user authentication algorithms, a lightweight convolutional neural network (CNN) channel feature extraction algorithm was proposed to reduce the channel state response required for training by changing the form of network input, and a multi-user physical layer channel feature-assisted authentication mechanism was established based on this algorithm to design a detailed process from user registration to authentication, and multi-user authentication and network parameter update online were completed.Simulation results show that the proposed algorithm can complete multi-user authentication, obtain good detection performance with smaller training rounds, and require fewer training samples than existing multi-user authentication algorithms.…”
Get full text

Improving the Accuracy of Batik Classification using Deep Convolutional Auto Encoder by Muhammad Faqih Dzulqarnain, Abdul Fadlil, Imam Riadi

“…The performance of this enhanced model was compared against a standard convolutional neural network (CNN) without the autoencoder. Experimental results demonstrate that the incorporation of the autoencoder significantly improved the classification accuracy, achieving 99% accuracy on the testing data and loss value of 3.4%. …”
Get full text

Pendeteksi Citra Masker Wajah Menggunakan CNN dan Transfer Learning by Mohammad Farid Naufal, Selvia Ferdiana Kusuma

“…Computer vision merupakan salah satu cabang ilmu komputer yang dapat digunakan untuk klasifikasi citra. Convolutional Neural Network (CNN) merupakan algoritma deep learning yang memiliki performa bagus dalam klasifikasi citra. …”
Get full text

Sistem Identifikasi Kesehatan Pencernaan Berdasar Suara Usus Menggunakan Embedded System by Ryzaldi Ananda Fabiana, Barlian Henryranu Prasetio, Eko Setiawan, Syahrul Chilmi, Edita Rosana Widasari

“…Sedangkan Convolutional Neural Network dengan model tensor flow digunakan sebagai metode klasifikasi dan MFCC teknik ekstraksi fiturnya. …”
Get full text

Comparison of Deep-Learning-Based Segmentation Models: Using Top View Person Images by Imran Ahmed, Misbah Ahmad, Fakhri Alam Khan, Muhammad Asif

“…The encoder consists of trained Convolutional Neural Network (CNN) to encode feature maps of the input image. …”
Get full text

Explainable Predictive Model for Suicidal Ideation During COVID-19: Social Media Discourse Study by Salah Bouktif, Akib Mohi Ud Din Khanday, Ali Ouni

“…We proposed a hybrid deep learning–based neural network approach (Bidirectional Encoder Representations from Transformers [BERT]+convolutional neural network [CNN]+long short-term memory [LSTM]) to classify suicidal and nonsuicidal posts. …”
Get full text

Physics-guided actor-critic reinforcement learning for swimming in turbulence by Christopher Koh, Laurent Pagnier, Michael Chertkov

“…Our scheme, coined the actor-physicist, is an adaptation of the actor-critic algorithm in which the neural network parameterized critic is replaced with an analytically derived physical heuristic function, the physicist. …”
Get full text

A Hybrid Model of Extreme Learning Machine Based on Bat and Cuckoo Search Algorithm for Regression and Multiclass Classification by Qinwei Fan, Tongke Fan

“…Extreme learning machine (ELM), as a new simple feedforward neural network learning algorithm, has been extensively used in practical applications because of its good generalization performance and fast learning speed. …”
Get full text

Pedestrian Detection Algorithm Combining Attention Mechanism and Nonmaximum Suppression Method by Duo Pan, Xuemei Zhou

“…Experimental results show that the detection accuracy of the proposed algorithm is significantly higher than that of the traditional convolutional neural network algorithm.…”
Get full text

Application of DBN deep learning algorithm in anti stealing electricity system by Dandan LI, Bingyu GE, Wenwen HUANG, Lei XIE, Shengqi QIAN

“…With the development of economy,the electric power demand increases gradually,but because of the relative backwardness in the automation of electricity,the phenomenon of electric stealing is common.But the traditional anti electric stealing means generally centered around how to strengthen the technical transformation of the electric energy metering device,and the management efficiency is low.The purpose of deep learning is to use the method of constructing the multi-layer neural network model.To learn the potential features of image,text,voice and other data,it also has good effect on the classification problem.The successful application of the deep learning algorithm in many complex fields provides a new effective way to solve the problem of anti stealing electricity.The structure and learning algorithm of DBN and the anti-stealing model based on DBN algorithm was mainly introduced.Finally,experiments were carried out and the results were analyzed.…”
Get full text

Robust Trajectory Tracking of Uncertain Systems via Adaptive Critic Learning by Ziliang Zhao, Qinglin Zhu, Bin Guo

“…To realize the optimal control, the derived Hamilton–Jacobi–Bellman equation (HJBE) is solved by training a critic neural network (CNN). Finally, two innovative critic learning techniques are suggested to calculate the unknown NN weights, where the convergence of NN weights can be guaranteed. …”
Get full text

Application of the ANFIS Approach in the Research of the Impact of Lubricant Viscosity on Rear Axle Transmission Efficiency by Mo Yimin, Xu Fang

“…For the problem of the impact of the lubricant viscosity on the rear axle transmission efficiency,by using the adaptive neural- network fuzzy inference method,a five- dimensional transmission efficiency controller based on ANFIS structure is designed. …”
Get full text

Improved Deep Learning Method for Intelligent Analysis of Sports Training Posture by Xianyou Yan

“…Thus, the stronger driving force of joint weights in the neural network is improved, the low importance of joint attention is reduced, and the high importance of joint attention is enhanced. …”
Get full text

Learner preferences prediction with mixture embedding of knowledge and behavior graph by Xiaoguang LI, Lei GONG, Xiaoli LI, Xin ZHANG, Ge YU

“…To solve the problems of inaccurate prediction of learner preference and insufficient utilization of structural information in the knowledge recommendation model, for the knowledge structure and learner behavior structure in the learner’s preference prediction model, the model of learner preferences predication with mixture embedding of knowledge and behavior graph was proposed.First, considering using graph convolution network (GCN) to fit structural information, GCN was extended to knowledge graph and behavior graph, the purpose of which was to obtain learners’ overall learning pattern and individual learning pattern.Then, the difference between knowledge structure and behavior structure was used to fit learners’ individual preferences, and recurrent neural network was used to encode and decode learners’ preferences to obtain the distribution of learners’ preference distribution.The experimental results on the real datasets demonstrate that the proposed model has a good effect on predicting learner preferences.…”
Get full text

Tomography of longitudinal phase space linearization for the generation of attosecond electron bunches by B. H. Schaap, P. Musumeci

“…Then, the initial and compensated phase of the picosecond electron bunch is precisely reconstructed by neural network assisted tomographic reconstruction from momentum spectra at varying buncher linac phase. …”
Get full text

Intelligent security relay selection for full duplex wireless communications by Fang LIU, Yajuan WANG, Zhengrong LAI, Yuan’an LIU

“…Full-duplex can double the spectrum efficiency theoretically.Thus it can further improve the spectrum efficiency when it is used in the relay systems.Considering the residual self-interference and signal-to-noise ratio,a problem was set to maximize the security capacity by selecting the optimal relay.This optimization problem was transformed into multi-classification problem.Thus a convolutional neural network (CNN)-based intelligent relay selection scheme was proposed.In the design of the classification model,the CNN was used to extract the spatial correlation of the channel,and the dimension of the convolution kernel was related to the number of relays.The pooling layer was not used to preserve the matrix characteristics of the input features.The simulation results show that the proposed CNN-based intelligent selection classification model has high classification accuracy,and can obtain the same security performance as the traditional exhaustive search scheme,and the real-time performance is significantly improved.…”
Get full text