Application effect of short-term traffic flow prediction method based on CNNBLSTM algorithm. by Guozhu Sui, Meixia Song, Ke Bian, Mingzhen Zhang, Xiaogang Zhang, Yiru Wang

“…Reduced forecast efficiency and accuracy are the result of traditional traffic flow prediction algorithms' inability to adequately capture the spatiotemporal characteristics and dynamic changes of traffic flow. To address this problem, this study proposes a short-term traffic flow prediction method based on an improved convolutional neural network and a bidirectional long short-term memory algorithm. …”
Get full text

Bearing Small Sample Fault Diagnosis based on Data Generation and Transfer Learning by Dinghui Wu, Qin Fang, Chuyi Wu

“…First of all， for the problems of class imbalance and data scarcity in the wind turbine bearing dataset， a data generation method based on a gate mechanism is proposed. …”
Get full text

Active Reinforcement Learning for the Semantic Segmentation of Urban Images by Mahya Jodeiri Rad, Costas Armenakis

“…The agent is represented by a deep Q-Network, where a Markov Decision Process (MDP) is used to formulate the Active Learning problem. …”
Get full text

Snow Leopard Infrared Camera Image Detection Method Based on Improved EfficientDet Model by DAI Tianhong, LIU Chao

“…Secondly, the Generative Adversarial Networks is used to transfer the domain of night infrared gray image, and the image prediction results before and after migration are fused to solve the problem of weak target recognition ability in infrared image.Finally, the attention mechanism is added to the backbone feature extraction network to refine the feature map to improve the visual significance of snow leopard in RGB and infrared images, and the improved feature fusion network structure to integrate more effective information. …”
Get full text

Two-Stage User Identification Based on User Topology Dynamic Community Clustering by Jiajing Zhang, Zhenhua Yuan, Neng Xu, Jinlan Chen, Juxiang Wang

“…In order to solve the problem of node information loss during user matching in the existing user identification method of fixed community across the social network based on user topological relationship, Two-Stage User Identification Based on User Topology Dynamic Community Clustering (UIUTDC) algorithm is proposed. …”
Get full text

IMP‐DETR: Optimization model for defect detection of injection‐moulded products by Anzhan Liu, Lei Han

“…Additionally, the Conv3XC‐Fusion module is designed to resolve the problem of integrating multi‐scale features, improving the stability of detection. …”
Get full text

Performance Analysis of Cognitive Radio System Based on Outage Probability of Cognitive Transmission by Haomin Gao, Haifeng Zhao, Xiao Liang, Xiaomin Mu

“…It is an important part to design an optimal spectrum sensing and transmission framework in cognitive radio network.Considering that cognitive data transmission outage had effect on the performance of cognitive radio system,a novel spectrum sensing and transmission model based on the outage probability of cognitive transmission was proposed and the two phases of spectrum sensing and data transmission were jointly optimized.The model was formulated as a nonconvex optimization problem under the constraint of interference to primary user,which maximized the average achievable throughput by the joint optimization of sensing time and data transmission rate and simulated by means of the numerical method.The numerical analysis shows that a better tradeoff can be achieved among the protection of primary user,the throughput of cognitive system and transmission delay when the outage probability is cited and the constraint is satisfied.…”
Get full text

Exchange rate forecasting with Artificial Intelligence by Katerina Zela (Male)

“…We discuss various forecasting approaches, including an Autoregressive Integrated. Moving Average model, a Nonlinear Autoregressive Neural Network model, a BATS model and Exponential Smoothing on the collected data and compare their accuracy using error term measuring indicators, choosing the model with the lowest Mean Absolute Percentage Error value. …”
Get full text

Research on PAPR reduction algorithm based on CWGAN-SLM for multi-wavelet OFDM system by Guang YANG, Zhaoyang WU, Min NIE, Xiaohong YAN, Fan JIANG

“…In order to meet the demand for low peak to average ratio (PAPR) of orthogonal frequency division multiplexing (OFDM) technology in the future 6G satellite-ground integrated system, an algorithm combining selective mapping (SLM) algorithm and multi-wavelet OFDM technology was proposed firstly.However, the PAPR reduction was limited and the computational complexity was high.To solve this problem, a multi-wavelet OFDM PAPR reduction algorithm based on conditional Wasserstein generative adversarial network (CWGAN) and SLM was proposed, which was called CWGAN-SLM algorithm.CWGAN was introduced to generate more time-domain alternative signals to reduce the PAPR in the CWGAN-SLM algorithm.Simulation results indicate that the CWGAN-SLM algorithm greatly reduces the PAPR of the system and the computational complexity, and has a lower bit error rate.Compared with the GAN and WGAN, the CWGAN has the advantages of easy training, strong stability and good PAPR performance.…”
Get full text

Assignment of hybrid laser and microwave inter-satellite links for navigation satellite systems by Nan Wang, Leyuan Sun, Yuankun Fang, Zhengkai Lu, Qiancheng Ding, Chengzhuo Wang, Wende Huang

“…Abstract A hybrid network comprising both laser and microwave inter-satellite links (ISLs) has been established within navigation satellite constellations. …”
Get full text

Improved printed circuit board defect detection scheme by Lufeng Bai, Wen Hao Xu

“…First, we incorporate the Efficient Channel Attention Network (ECANet) attention mechanism into the backbone network of YOLOv8, which improves the performance of small-target detection by adaptively enhancing the expressiveness of key features, so that the network possesses higher sensitivity and focus on tiny details in PCB images. …”
Get full text

A Detection Method for Conveyor Belt Damage with Small Size and Low Contrast by HAN Yajie, HAO Xiaoli, NIU Baoning, XUE Jindong

“…[Methods] In order to solve the problem of small size, first, the DDS unit is designed to replace the Res unit in the backbone network. …”
Get full text

Small target detection in coal mine underground based on improved RTDETR algorithm by Feng Tian, Cong Song, Xiaopei Liu

“…A new BasicBlock-PConv module was created by incorporating Partial Convolutions (PConv) into the conventional BasicBlock, which was based on the FasterNet network. This decreased the number of network parameters and computation. …”
Get full text

An Enhanced Starfish Optimization Algorithm via Joint Strategy and Its Application in Ultra-Wideband Indoor Positioning by Yu Liu, Maosheng Fu, Zhengyu Liu, Huaiqing Liu, Wei Peng, Ling Li, Yang Yang, Xiancun Zhou, Chaochuan Jia

“…The results showed that the SFOAL-BP neural network had a smaller average position error compared to the random BP neural network and the SFOA-BP neural network, so it can be used to solve practical application problems.…”
Get full text

Comparison of Style Features for the Authorship Verification of Literary Texts by Ksenia Vladimirovna Lagutina

“…AdaBoost and a neural network with an LSTM layer are considered as classification algorithms. …”
Get full text

Foreign object detection on coal conveyor belt enhanced by attention mechanism by ZHANG Yang, CHENG Zhiyu, CHEN Yunjiang, ZHANG Jiannan, YUAN Wensheng, ZHANG Hui

“…In order to solve this problem, the network structure of the original YOLOv8 algorithm was optimized and a YOLOv8-CPCA detection method was proposed. …”
Get full text

Dynamic programming for home appliance scheduling with renewable energy integration by Iqra Rafiq, Anzar Mahmood, Ubaid Ahmed, Imran Aziz, Zafar Ali Khan

“…This study proposes an energy cost minimization model, which is solved using a single Knapsack algorithm combined with dynamic programming (DP). The Knapsack problem is used to schedule appliances and ensure that users and producers receive the maximum benefits in terms of cost minimization and peak-to-average ratio (PAR) reduction. …”
Get full text

Position Accuracy Improvement of the Inertial Navigation System using LSTM Algorithm without GNSS Signals by Mohammad Sabzevari, MasoudReza Aghabozorgi Sahaf

“…One of the methods used to solve this problem is by using inertial navigation systems as an auxiliary system. …”
Get full text

Efficient resource allocation in cloud environment using SHO-ANN-based hybrid approach by Sanjeev Sharma, Pradeep Singh Rawat

“…This manuscript proposes a hybrid Spotted Hyena optimizer and artificial neural network, named the SHO-ANN technique, to provide a solution to the virtual machine assignment problem. …”
Get full text

An improved multi-object instance segmentation based on deep learning by Nawaf Alshdaifat, Mohd Azam Osman, Abdullah Zawawi Talib

“… Given the recent breakthroughs in recent years, Deep learning (DL) networks have attracted growing interest and attention by researchers and scholars alike due to its importance in detecting and instance segmentation of objects in an image. …”
Get full text