SpeakerNet for Cross-lingual Text-Independent Speaker Verification by Hafsa HABIB, Huma TAUSEEF, Muhammad Abuzar FAHIEM, Saima FARHAN, Ghousia USMAN

“…Extracted features from Siamese then can be classified using difference or correlation measures. We have implemented a customized scoring scheme that utilizes Siamese’ capability of applying distance measures with the convolutional learning. …”
Get full text

BPFun: a deep learning framework for bioactive peptide function prediction using multi-label strategy by transformer-driven and sequence rich intrinsic information by Lun Zhu, Hao Sun, Sen Yang

“…Meanwhile, adopting data augmentation to solve the problem of data imbalance. We combine convolutional networks of different scales and Bi-LSTM layers to obtain high-level feature vectors of different features. …”
Get full text

Using VGG Models with Intermediate Layer Feature Maps for Static Hand Gesture Recognition by Osamah Y. Fadhil, Bashar S. Mahdi, Ayad R. Abbas

Get full text

Ulcer detection in Wireless Capsule Endoscopy images using deep CNN by Vani V, K.V. Mahendra Prashanth

“…In this paper, we propose deep Convolutional Neural Network(CNN) for automatic discrimination of ulcers on different ratios of augmented datasets ranging from 1000 to 10000 WCE images comprising of ulcer and non-ulcer images. …”
Get full text

Efficient Deep Learning Job Allocation in Cloud Systems by Predicting Resource Consumptions including GPU and CPU by Abuda Chad Ferrino, Tae Young Choe

Get full text

Clothing classification method based on attention mechanism and transfer learning by CHEN Jinguang, HUANG Xiaoju, MA Lili

“…Image dataset was processed by data augmentation of geometric transform and color jitter to improve the generalization ability of the model. Convolutional block attention module (CBAM) was added to the ResNet50-based network, and attention of different region of clothing was improved from both channel and spatial dimensions in turn. …”
Get full text

Research progress in globular fruit picking recognition algorithm based on deep learning by LI Hui, ZHANG Jun, YU Shuochen, LI Zhixin

“…China is a global leader in fruit production, and fruit picking mainly relies on manual labor, which helps to select fruits according to fruit size and quality to reduce loss in this way. Different techniques and tools can be adopted according to the characteristics and picking needs of each fruit crop. …”
Get full text

DETERMINATION OF THE BEST OPTIMIZER FOR A NEURONETWORK IN THE DEVELOPMENT OF AUTOMATIC IMAGE TAGGING SYSTEMS by Andrian Kozynets

“…The neural networks were trained on two different datasets with significantly different characteristics. …”
Get full text

Load Forecasting Based on Multiple Load Features and TCN-GRU Neural Network by Haofeng ZHENG, Guohua YANG, Wenjun KANG, Zhiyuan LIU, Shitao LIU, Hong WU, Honghao ZHANG

“…Firstly, the load change rate feature and the load component feature based on the ensemble empirical mode decomposition are introduced, and the feature combination MLFC is formed with the load and date features; Second, select TCN and GRU for feature extraction and prediction, and build an MLFC-TCN-GRU prediction framework based on MLFC; Finally, using different models to verify the proposed method, the results show that MLFC helps to improve the prediction accuracy and is suitable for different models; at the same time, MLFC-TCN-GRU has the highest prediction accuracy compared with other models.…”
Get full text

Research on algorithm for improving imaging accuracy of CFRP low speed impact damage by WU Xiangnan, CHENG Xiaojin, LI Qixin, SHANG Jianhua

“…The iterative training results demonstrate that when the iteration count reaches 200，the σEOL of different types of impact damage is greater than 1. …”
Get full text

Research on the Timing of Replacing Worn Milling Cutters by Using Wear Transition Percentage Constructed Based on Spindle Current Clutter Signals by Zhihao Liu, Min Wang, Zhishan Wang, Tao Zan, Xiangsheng Gao, Peng Gao

“…Finally, the model is used to identify the full life SCCS data with different cutting parameters. The proportion of samples identified as normal wear to all samples during a certain period of time is used to calculate the wear transition percentage. …”
Get full text

Encrypted traffic identification method based on deep residual capsule network with attention mechanism by Guozhen SHI, Kunyang LI, Yao LIU, Yongjian YANG

“…With the improvement of users’ security awareness and the development of encryption technology, encrypted traffic has become an important part of network traffic, and identifying encrypted traffic has become an important part of network traffic supervision.The encrypted traffic identification method based on the traditional deep learning model has problems such as poor effect and long model training time.To address these problems, the encrypted traffic identification method based on a deep residual capsule network (DRCN) was proposed.However, the original capsule network was stacked in the form of full connection, which lead to a small model coupling coefficient and it was impossible to build a deep network model.The DRCN model adopted the dynamic routing algorithm based on the three-dimensional convolutional algorithm (3DCNN) instead of the fully-connected dynamic routing algorithm, to reduce the parameters passed between each capsule layer, decrease the complexity of operations, and then build the deep capsule network to improve the accuracy and efficiency of recognition.The channel attention mechanism was introduced to assign different weights to different features, and then the influence of useless features on the recognition results was reduced.The introduction of the residual network into the capsule network layer and the construction of the residual capsule network module alleviated the gradient disappearance problem of the deep capsule network.In terms of data pre-processing, the first 784byte of the intercepted packets was converted into images as input of the DRCN model, to avoid manual feature extraction and reduce the labor cost of encrypted traffic recognition.The experimental results on the ISCXVPN2016 dataset show that the accuracy of the DRCN model is improved by 5.54% and the training time of the model is reduced by 232s compared with the BLSTM model with the best performance.In addition, the accuracy of the DRCN model reaches 94.3% on the small dataset.The above experimental results prove that the proposed recognition scheme has high recognition rate, good performance and applicability.…”
Get full text

Regional distributed photovoltaic power forecasting considering spatiotemporal correlation and meteorological coupling by HUANG Xiaoyan, GUO Sasa, CHEN Chengyou, XU Tengchong, HAN Xiao, WANG Tao

“…Additionally， a neural network layer with non-shared parameters is employed to capture the coupling relationship between different photovoltaic stations and meteorological factors， enabling the forecasting of power generation across multiple stations. …”
Get full text

Research on Pork Cut and Freshness Determination Method Based on Computer Vision by Shihao Song, Qiqi Guo, Xiaosa Duan, Xiaojing Shi, Zhenyu Liu

“…To improve the precision and efficiency of pork quality assessment, an automated detection method based on computer vision technology is proposed for evaluating different parts and freshness of pork. First, high-resolution cameras were used to capture image data of Jinfen white pigs, covering three pork cuts—hind leg, loin, and belly—across three different collection times. …”
Get full text

Additive Attention for Vetting Transiting Exoplanet Candidates by Àlvar Hernàndez-Carnerero, Miquel Sànchez-Marrè, Juan Carlos Morales

Get full text

Impact of Dataset Size on 3D CNN Performance in Intracranial Hemorrhage Classification by Chun-Chao Huang, Hsin-Fan Chiang, Cheng-Chih Hsieh, Bo-Rui Zhu, Wen-Jie Wu, Jin-Siang Shaw

“…The performance of AI models varies across different ICH types and is more stable with larger sample sizes.…”
Get full text

Green Ground: Construction and Demolition Waste Prediction Using a Deep Learning Algorithm by Wadha N. Alsheddi, Shahad E. Aljayan, Asma Z. Alshehri, Manar F. Alenzi, Norah M. Alnaim, Maryam M. Alshammari, Nouf K. AL-Saleem, Abdulaziz I. Almulhim

“…The waste management and recycling industry in Saudi Arabia is facing ongoing challenges in reducing the negative impact resulting from the recycling process. Different types of waste lack an efficient and accurate method for classification, especially in cases that require the rapid processing of materials. …”
Get full text

Transfer learning-enhanced CNN-GRU-attention model for knee joint torque prediction by Hao Xie, Yingpeng Wang, Tingting Liu, Songhua Yan, Jizhou Zeng, Kuan Zhang

Get full text

PlantDeepMeth: A Deep Learning Model for Predicting DNA Methylation States in Plants by Zhongwei Guo, Wenyuan Fan, Chengcheng Cai, Kang Zhang, Xilin Hou, Ying Li, Feng Cheng

Get full text

The Application of Deep Learning for Lymph Node Segmentation: A Systematic Review by Jingguo Qu, Xinyang Han, Man-Lik Chui, Yao Pu, Simon Takadiyi Gunda, Ziman Chen, Jing Qin, Ann Dorothy King, Winnie Chiu-Wing Chu, Jing Cai, Michael Tin-Cheung Ying

“…This study evaluates the application of deep learning in lymph node segmentation and discusses the methodologies of various deep learning architectures such as convolutional neural networks, encoder-decoder networks, and transformers in analyzing medical imaging data across different modalities. …”
Get full text