Hyperspectral Image Classification Based on Attentional Residual Networks by Ning Wang, Xin Pan, Xiaoling Luo, Xiaojing Gao

“…Firstly, the residual network is used to extract the features of hyperspectral images, and the quality of feature extraction is effectively improved by solving the problem of gradient disappearance and gradient explosion in deep neural network training. Then, the Attention Module (AM) is introduced to optimize the feature extraction process, so that the model can focus on the important regions in the image. …”
Get full text

Building Arabic Speech Recognition System Using HuBERT Model and Studying the Sources of Errors [Arabic] by Rima Sbih, Assef Jafar, Ali Kazem

“…This paper presents the development of a speech recognition system for the Arabic language that can handle continuous speech and a large number of words, independent of the speaker, using deep neural network models trained by self-supervised learning. …”
Get full text

Safely Imitating Predictive Control Policies for Real-Time Human-Aware Manipulator Motion Planning: A Dataset Aggregation Approach by Aigerim Nurbayeva, Matteo Rubagotti

“…This paper proposes a dataset-aggregation approach for imitating a nonlinear model predictive control law via deep neural networks, to safely allow a robot manipulator to share its workspace with a human operator. …”
Get full text

Abnormal traffic detection method based on LSTM and improved residual neural network optimization by Wengang MA, Yadong ZHANG, Jin GUO

“…Problems such as a difficulty in feature selection and poor generalization ability were prone to occur when traditional method was exploited to detect abnormal network traffic.Therefore, an abnormal traffic detection method based on the long short term memory network (LSTM) and improved residual neural network optimization was proposed.Firstly, the features and attributes of network traffic were analyzed, and the variability of the feature values was reduced by preprocessing of network traffic.Then, a three-layer stacked LSTM network was designed to extract network traffic features of different depths.Moreover, the problem of weak adaptability of feature extraction was solved.Finally, an improved residual neural network with skipping connecting line was designed to optimize the LSTM.The defects of deep neural network such as overfitting and gradient vanishing were optimized.The accuracy of abnormal traffic detection was improved.Experimental results show that the proposed method has higher training accuracy and better visibility of data processing.The classification accuracy rates under two classifications and multiple classifications are 92.3% and 89.3%.It has the lowest false positive rate when the parameters such as precision rate and recall rate are optimal.Moreover, it has strong robustness when the sample is destroyed.Furthermore, better generalization ability can be achieved.…”
Get full text

Detection freezing of gait (FOG) in Parkinson's patients using wearable sensors and deep learning by Maryam Talebvand, Amir Lakizadeh, Faranak Fotouhi

“…The proposed methoddetects FOG by providing a deep neural network architecture based on two-way short-term memory networks (BDL-FOG). …”
Get full text

Multisegment Mapping Network for Massive MIMO Detection by Yongzhi Yu, Jianming Wang, Limin Guo

“…This paper proposes a deep neural network for massive MIMO detection, named Multisegment Mapping Network (MsNet). …”
Get full text

Classification of NSCLC subtypes using lung microbiome from resected tissue based on machine learning methods by Pragya Kashyap, Kalbhavi Vadhi Raj, Jyoti Sharma, Naveen Dutt, Pankaj Yadav

“…Next, benchmarking was performed across six different supervised-classification algorithms viz. logistic-regression, naïve-bayes, random-forest, extreme-gradient-boost (XGBoost), k-nearest neighbor, and deep neural network. Noteworthy, XGBoost, with an accuracy of 76.25%, and AUROC (area-under-receiver-operating-characteristic) of 0.81 with 69% specificity and 76% sensitivity, outperform the other five classification algorithms using LDA-transformed features. …”
Get full text

Radar Jamming Recognition: Models, Methods, and Prospects by Zan Wang, Zhengwei Guo, Gaofeng Shu, Ning Li

“…Furthermore, the focus shifts to neural network-based methods, such as shallow neural network methods and deep neural network methods. In particular, restricted sample strategies are also discussed as potential future directions. …”
Get full text

Thermal Heating in ReRAM Crossbar Arrays: Challenges and Solutions by Kamilya Smagulova, Mohammed E. Fouda, Ahmed Eltawil

“…In addition, it reviews the available solutions designed to mitigate the impact of these challenges, including emerging temperature-resilient Deep Neural Network (DNN) training methods. Our work also provides a summary of the techniques and their advantages and limitations.…”
Get full text

Robust Face Detection and Identification under Occlusion using MTCNN and RESNET50 by Eiman Wahab, Wajeeha Shafique, Habiba Amir, Sameena Javed, Muhammad Marouf

“…Our project utilizes the power of deep learning model: Residual Network (ResNet50), the form of deep neural network architectures well-suited for the job of features extraction. …”
Get full text

2.5D Facial Personality Prediction Based on Deep Learning by Jia Xu, Weijian Tian, Guoyun Lv, Shiya Liu, Yangyu Fan

“…Our experimental results show that the deep neural network trained by large labeled datasets can reliably predict people’s multidimensional personality characteristics through 2.5D static facial contour images, and the prediction accuracy is better than the previous method using 2D images.…”
Get full text

Reconstruction of Three-Dimensional Porous Media Using Deep Transfer Learning by Yi Du, Jie Chen, Ting Zhang

“…Hence, a method for reconstructing porous media is presented by applying DTL to extract features from a training image (TI) of porous media to replace the process of scanning a TI for different patterns as in multiple-point statistical methods. The deep neural network is practically used to extract the complex features from the TI of porous media, and then, a reconstructed result can be obtained by transfer learning through copying these features. …”
Get full text

Application of Machine Learning in Multi-Directional Model to Follow Solar Energy Using Photo Sensor Matrix by P. Dhanalakshmi, V. Venkatesh, P. S. Ranjit, N. Hemalatha, S. Divyapriya, R. Sandhiya, Sumit Kushwaha, Asmita Marathe, Mekete Asmare Huluka

“…In this paper, we introduce a deep neural network (DNN) for forecasting the intra-day solar irradiance, photovoltaic PV plants, regardless of whether or not they have energy storage, can benefit from the work being done here. …”
Get full text

Accurate Recognition and Simulation of 3D Visual Image of Aerobics Movement by Wenhua Fan, Hyun Joo Min

“…A lot of results have been achieved by applying deep neural networks to the 3D visual image recognition of aerobics movements, but there are still many problems to be overcome. …”
Get full text

An Enhancement Deep Feature Extraction Method for Bearing Fault Diagnosis Based on Kernel Function and Autoencoder by Fengtao Wang, Bosen Dun, Xiaofei Liu, Yuhang Xue, Hongkun Li, Qingkai Han

“…Subsequently, a deep neural network is constructed with one KAE and multiple AEs to extract inherent features layer by layer. …”
Get full text

The Fault Diagnosis of Rolling Bearing Based on Improved Deep Forest by Xiwen Qin, Dingxin Xu, Xiaogang Dong, Xueteng Cui, Siqi Zhang

“…At present, the technology of intelligent identification of bearing mostly relies on deep neural network, which has high requirements for computer equipment and great effort in hyperparameter tuning. …”
Get full text

Anti-Diabetic Therapeutic Medicinal Plant Identification Using Deep Fused Discriminant Subspace Ensemble (D2SE) by N. Sasikaladevi, S. Pradeepa, A. Revathi, S. Vimal, Gaurav Dhiman

“…They may act as an alternative source of antidiabetic agents. The fused deep neural network (DNN) model with Discriminant Subspace Ensemble is designed to identify the diabetic plants from VNPlant200 data set. …”
Get full text

Gradient Enhancement Techniques and Motion Consistency Constraints for Moving Object Segmentation in 3D LiDAR Point Clouds by Fangzhou Tang, Bocheng Zhu, Junren Sun

“…In this paper, we introduce a novel deep neural network designed to enhance the performance of 3D LiDAR point cloud moving object segmentation (MOS) through the integration of image gradient information and the principle of motion consistency. …”
Get full text

A Semi-supervised Deep Learning Method for Cervical Cell Classification by Siqi Zhao, Yongjun He, Jian Qin, Zixuan Wang

“…Cervical cell classification is a key technology in the intelligent cervical cancer diagnosis system. Training a deep neural network-based classification model requires a large amount of data. …”
Get full text

Application of Improved Naive Bayesian-CNN Classification Algorithm in Sandstorm Prediction in Inner Mongolia by Li Tiancheng, Ren Qing-dao-er-ji, Qiu Ying

“…Convolutional neural network (CNN) is a deep neural network with convolution structure, which can automatically learn features from massive data. …”
Get full text