Deep Feature Learning for Intrinsic Signature Based Camera Discrimination by Chaity Banerjee, Tharun Kumar Doppalapudi, Eduardo Pasiliao, Tathagata Mukherjee

Get full text

A Machine Learning Based Framework for a Stage-Wise Classification of Date Palm White Scale Disease by Abdelaaziz Hessane, Ahmed El Youssefi, Yousef Farhaoui, Badraddine Aghoutane, Fatima Amounas

Get full text

Enhancing Telemarketing Success Using Ensemble-Based Online Machine Learning by Shahriar Kaisar, Md Mamunur Rashid, Abdullahi Chowdhury, Sakib Shahriar Shafin, Joarder Kamruzzaman, Abebe Diro

Get full text

Automated Observations of the Earthshine by P. R. Goode, S. Shoumko, E. Pallé, P. Montañés-Rodríguez

“…We have designed and implemented small aperture, remote control telescopes in Big Bear Solar Observatory in California and in Tenerife in the Canary Islands. …”
Get full text

GCL_FCS30: a global coastline dataset with 30-m resolution and a fine classification system from 2010 to 2020 by Jian Zuo, Li Zhang, Jingfeng Xiao, Bowei Chen, Bo Zhang, Yingwen Hu, M. M. Abdullah Al Mamun, Yang Wang, Kaixin Li

Get full text

Early Warning Model of Sports Injury Based on RBF Neural Network Algorithm by Fuxing He

“…In this paper, we use a neural network to realize big data analysis of sports injury data. Big data network is a method of capturing Internet information by means of cloud computing, which is usually used in the construction of Wan and LAN. …”
Get full text

Angus: efficient active learning strategies for provenance based intrusion detection by Lin Wu, Yulai Xie, Jin Li, Dan Feng, Jinyuan Liang, Yafeng Wu

“…Abstract As modern attack methods become more concealed and complex, obtaining many labeled samples in big data streams is difficult. Active learning has long been used to achieve better intrusion detection performance by using only a small number of training samples. …”
Get full text

Finite Element Calculation and Its Test Study of Flexible Pin Structure in the 3.X MW Wind Turbine Gearbox by Jinku Li, Wei Liu, Liangrong Li

“…The stress and the displacement of the planetary gear train under rated working conditions are analyzed. …”
Get full text

Imagen aérea de Villeneuve-Saint-Georges (agosto de 2017) by Teresa Artal Borrás

“…Here we can observe the fluvial and land transportation, an important train intersection and also several roads. …”
Get full text

Imagen aérea de Villeneuve-Saint-Georges (agosto de 2017) by Teresa Artal Borrás

“…Here we can observe the fluvial and land transportation, an important train intersection and also several roads. …”
Get full text

Perspectives on Soft Actor–Critic (SAC)-Aided Operational Control Strategies for Modern Power Systems with Growing Stochastics and Dynamics by Jinbo Liu, Qinglai Guo, Jing Zhang, Ruisheng Diao, Guangjun Xu

“…Nevertheless, coordinating various types of resources to derive effective online control decisions for a large-scale power network remains a big challenge. To tackle the limitations of existing control approaches that require full-system models with accurate parameters and conduct real-time extensive sensitivity-based analyses in handling the growing uncertainties, this paper presents a novel data-driven control framework using reinforcement learning (RL) algorithms to train robust RL agents from high-fidelity grid simulations for providing immediate and effective controls in a real-time environment. …”
Get full text

A Data-Driven Urban Metro Management Approach for Crowd Density Control by Hui Zhou, Zhihao Zheng, Xuekai Cen, Zhiren Huang, Pu Wang

“…Large crowding events in big cities pose great challenges to local governments since crowd disasters may occur when crowd density exceeds the safety threshold. …”
Get full text

Causal Discovery Evaluation Framework in the Absence of Ground-Truth Causal Graph by Tingpeng Li, Lei Wang, Danhua Peng, Jun Liao, Li Liu, Zhendong Liu

Get full text

A method of synthetic speech spoofing detection using constant Q modulation envelope by Jia XU, Zhihua JIAN, Honghui JIN, Chao WU

“…In response to the low accuracy of synthetic speech spoofing detection based on traditional acoustic feature parameters, poor detection performance for unknown types of synthetic speech, and performance degradation in noisy environments, a method for detecting spoofing synthetic speech was proposed using constant Q modulation envelope (CQME) .The motivation of the method was from the fact that the temporal envelope of speech contained abundant information and there was a big difference in detail between the envelope of synthetic speech and genuine speech.The modulation envelope spectrum of speech was obtained by employing constant Q transform (CQT), and the root mean square of each frequency component was calculated to derive the CQME feature vector.And then the CQME feature vector was used to train the random forest classifier for discriminating genuine speech from spoofing synthetic speech.Experimental results demonstrate that the random forest trained with CQME features achieves high detection performance on the ASVspoof 2019 dataset and exhibites good detection efficacy for unknown types of synthetic speech.Furthermore, the proposed method shows high detection performance even under various noise conditions, having excellent noise robustness.…”
Get full text

(Un)stable diffusions by Fenwick McKelvey, Joanna Redden, Jonathan Roberge, Luke Stark

“…Without public data and public participation, these large models could not be trained. Without the attention, hype, and hope around these technologies, the big AI firms probably could not afford the computational costs to train these models. …”
Get full text

Research on Commercial Bank Risk Early Warning Model Based on Dynamic Parameter Optimization Neural Network by Yiming Wang

“…Based on the background of big data, it is necessary to study the dynamic parameter optimization of the commercial bank risk model neural network. …”
Get full text

Clinical Treatment and Nursing Intervention Study of Clipping Treatment of Cerebral Aneurysm under the Health Model of Data Analysis by Yuyou Huang, Liping Huang

“…This paper studies data analytics health models in the context of big data analytics. The model combines the characteristics of cerebral aneurysms for targeted analysis, and then through the understanding of the clipping treatment of cerebral aneurysms, this paper combines the deep learning in the neural network to train the treatment plan under the data analysis health model. …”
Get full text

Study on the Effect of Air Throttling on Flame Stabilization of an Ethylene Fueled Scramjet Combustor by Ye Tian, Shunhua Yang, Jialing Le

“…The results were obtained under the inflow condition with Mach number of 2.0, total temperature of 900 K, total pressure of 0.8 MPa, and total equivalence ratio of 0.5. The shock train generated by air throttling had a big effect on the flow structure of the scramjet combustor. …”
Get full text

A 3D Dual Encoder Mirror Difference ResU-Net for Multimodal Brain Tumor Segmentation by Qiwei Xing, Zhihua Li, Yongxia Jing, Xiaolin Chen

Get full text

Development and validation of a nomogram for predicting venous thromboembolism risk in post-surgery patients with cervical cancer by Yue Chen, Xiaosheng Li, Li Yuan, Yuliang Yuan, Qianjie Xu, Zuhai Hu, Wei Zhang, Haike Lei

Get full text