Intelligent Attitude Control of Hypersonic Vehicle Based on DDQN and Deep Q-Learning from Demonstrations by Liu Jingwen, Cai Guangbin, Fan Yonghua, Fan Hongdong, Wu Tong, Shang Yiming

“…The simulation results show that the reinforcement learning method based on demonstration data can track control command, realize the attitude control of hypersonic vehicle, and improve the performance of neural network in the early stage of training, with a higher average reward.…”
Get full text

Tunable Energy-Efficient Approximate Circuits for Self-Powered AI and Autonomous Edge Computing Systems by Shubham Garg, Kanika Monga, Nitin Chaturvedi, S. Gurunarayanan

“…Additionally, recent advancements in Deep Neural Network (DNN) running on millions of devices for various AI tasks deliver an accuracy comparable to human levels. …”
Get full text

Dynamic effect on turnouts of cars having wheelsets with thin flanges by B. E. Glyuzberg, M. I. Titarenko, E. A. Timakova, A. A. Savchenko, S. V. Kuznetsov, А. M. Kalachev

“…Currently, a very topical issue is the question of a possible adjustment of the regulatory framework in the “wheelset—rail track” system in order to take into account the actual state of the track, turnouts and wheel park on the railway network.Any changes made in order to reduce the maintenance of wheelsets or tracks are possible only when the safety of train traffic is unconditionally ensured.The most difficult problem in determining the possibility of changing the standard for the minimum thickness of the flange of car wheels is the problem of passing the turnouts. …”
Get full text

Analysis and prediction of infectious diseases based on spatial visualization and machine learning by Yunyun Cheng, Yanping Bai, Jing Yang, Xiuhui Tan, Ting Xu, Rong Cheng

“…Then, autoregressive integrated moving average model (ARIMA), extreme learning machine (ELM), support vector regression (SVR), wavelet neural network (Wavelet), recurrent neural network (RNN) and long short-term memory (LSTM) were used to predict COVID-19 epidemic data in Guangdong Province, China; And the prediction performance of each model was compared through prediction accuracy indicators. …”
Get full text

Enhanced zebra optimization algorithm and applications of power allocation in SDWN by LI Jiajia, DONG Ligang, JIANG Xian

“…In the SDWN power allocation problem, EZOA achieves an average improvement of 5.46% in user secrecy rate and the fastest convergence speed compared to five other algorithms.…”
Get full text

Semantic Segmentation of Aerial Laser Point Clouds Based on Deep-Residual Enhanced Coding of Multi-Feature Information by Xin Luo, Peng Lin, Xiaoxi Li, Zuqi Wei, Hai Li

“…Meanwhile, ‘Dropout’ operations are applied to the fully connected layer to cope with the problem that the model is prone to overfitting due to many network parameters. …”
Get full text

Port terminal mobile recognition based on combined YOLOv5s-DeepSort. by Chengzhi Wang, Donghong Chen, Zhen Liu, Yuanhao Li, Yifei Wang, Sanglan Zhao

“…The findings indicate that incorporating multi-scale convolution into YOLOv5s improved the robustness of multi-scale object detection, resulting in a 0.4% increase in mean Average Precision (mAP). Furthermore, the integration of an efficient pyramid segmentation attention (EPSA) network enhanced the accuracy of multi-scale feature fusion representation. …”
Get full text

LBT-YOLO: A Lightweight Road Targeting Algorithm Based on Task Aligned Dynamic Detection Heads by Pei Tang, Zhenyu Ding, Minnan Jiang, Weikai Xu, Mao Lv

“…Secondly, a new neck network structure BCFPN (Bidirectional Collocated Feature Pyramid Network) is designed based on the weighted bidirectional feature pyramid network, which enhances the feature fusion and the interaction of contextual information, and improves the detection accuracy of the model. …”
Get full text

Deep learning-based prediction of multi-level just noticeable distortion by Haifeng XU, Hongkui WANG, Haibing YIN, Chuqiao CHEN

“…Visual just noticeable distortion (JND) directly reflects the sensitivity of the human visual system to visual signal noise, and is widely used in image and video processing.Aiming at the multilevel prediction problem of video JND threshold, it was transformed into the prediction problem of satisfied user ratio (SUR) curve, and a feature fusion-based SUR curve prediction model was proposed.The model was mainly divided into key frame extraction module, feature extraction and fusion module, and SUR score regression module.In the key frame extraction module, according to the visual perception mechanism, the spatial-temporal domain perception complexity was proposed and used as the video key frame judgment index.In the feature extraction and fusion module, a multi-scale dense residual network was proposed based on dense residual block (RDB) to realize image feature extraction and multi-scale fusion.The experimental results show that the proposed SUR curve prediction model is overall better than the existing models in terms of JND prediction accuracy and reduces the time cost by 8.1% on average in terms of operational efficiency.Meanwhile, the model can also be used to predict other layers of JND thresholds, which can be directly applied to video multilevel perceptual coding optimization.…”
Get full text

Application of Improved MDSMOTE and FC-SVM in Imbalanced Data Set Classification by WEN Xue-yan, ZHAO Li-ying, XU Ke-sheng, LU Guang

“…On the network shopping evaluation data sets appear the phenomenon of extreme imbalance，inorder to improve the classification accuracy of the unbalanced data set，It should be improved from both the sample and the algorithm For one of the problem in MDSMOTE algorithm that when generating part of the new samples， wrong points sample can't be contained，the correct classification of the wrongly classified sample is added to the existing MDSMOTE algorithm to improve the quality of the samples. …”
Get full text

Research on Nonlinear Time Series Processing Method for Automatic Building Construction Management by Yunbing Liu

“…By comparing the results, the maximum relative error of BP network prediction is 18.59%, while the maximum relative error of RBF network prediction is 29.16%, and the average relative error of 13P network prediction is 7.02%, while the average relative error of RBF network prediction value is 10.5%. …”
Get full text

Personalized learning effect evaluation model for vocational education with cloud computing technology by Xiangyu Wang, Kang Cao

“…However, online teaching under CCT still has the problem of unstable teaching quality, so the study establishes a relevant learning effect evaluation model for the personalized learning platform of vocational education under CCT. …”
Get full text

Economic analysis of specialized dairy farms in Croatia according to FADN by Vesna Očić, Branka Šakić Bobić, Zoran Grgić

“…The Farm Accountancy Data Network (FADN) enables analysis and comparison of farms business data, and the dairy sector has been selected because of its great importance in the European Union (EU). …”
Get full text

The GPR-based estimation of the volumetric ice content of dispersed ground in the Central Yakut lowland by L. G. Neradovsky

“…The  proposed method of reusable measurements of signals of georadiolocation with changing position and azimuth of antennas of georadars in the vicinity of the network points of geological and geophysical observations allows to estimate the average values of the propagation speed and specific attenuation of electromagnetic waves with an error of not more than 10%. …”
Get full text

Research on underwater disease target detection method of inland waterway based on deep learning by Tao Yu, Yu Xie, Jinsong Luo, Wei Zhu, Jie Liu

“…Then, EIoU is used as the frame loss function to speed up the network convergence rate and solve the problem of difficult and easy sample imbalance. …”
Get full text

A Hybrid Attention Mechanism and RepGFPN Method for Detecting Wall Cracks in High-Altitude Cleaning Robots by Haiqiao Liu, Lingding Li, Ya Li, Qing Long, Zhuoyu Chen

“…Aiming at the problem that cracks with different shapes and scales on the exterior walls of high buildings are difficult to detect, this paper proposed a wall crack detection method for high-altitude cleaning robots by hybridizing the GAM attention mechanism and RepGFPN. …”
Get full text

Third Ventricle Width Measurements Based on YOLO and Localized Intensity Features by Xiao Zhou, Ao Wan, Xingang Mou, Hongling Gao, Zheng Xue

“…The YOLO-TV model introduces a multi-head attention mechanism in the feature extraction network to enhance the network to extract feature at different scales. …”
Get full text

Enhanced Driver Posture Feature Extraction Method Based on the Spatial Prior Probabilistic Model by WANG Han; SUN Yu; YIN Jie

“…Moreover, the average recognition rate under the combination of neural network and proposed method is 12% higher than other traditional methods.…”
Get full text

Wide-Range Variable Cycle Engine Control Based on Deep Reinforcement Learning by Yaoyao Ding, Fengming Wang, Yuanwei Mu, Hongfei Sun

“…A comparison of the simulation results shows that the proposed deep reinforcement learning controller effectively addresses the engine’s multi-variable coupling control problem. In addition, it reduces response time by an average of 44.5%, while maintaining a similar overshoot level to that of the PID controller.…”
Get full text

Machine learning models for predicting residual malaria infections using environmental factors: A case study of the Jazan region, Kingdom of Saudi Arabia by Idris Zubairu Sadiq, Yakubu Saddeeq Abubakar, Abdulkadir Rabiu Salisu, Babangida Sanusi Katsayal, Umar Saidu, Sani I. Abba, Abdullahi Garba Usman

“…Background: Malaria is a global public health problem affecting more than 100 countries. Meteorological factors on the other hand represent a major driving force behind malaria transmission and other vector-borne diseases. …”
Get full text