Universal Knowledge Graph Embedding Framework Based on High-Quality Negative Sampling and Weighting by Pengfei Zhang, Huang Peng, Yang Fang, Zongqiang Yang, Yanli Hu, Zhen Tan, Weidong Xiao

“…The traditional model training approach based on negative sampling randomly samples a portion of negative samples for training, which can easily overlook important negative samples and adversely affect the training of knowledge graph embedding models. …”
Get full text

Efficient Implementation of Matrix-Based Image Processing Algorithms for IoT Applications by Sorin Zoican, Roxana Zoican

Subjects: Get full text

Improved Cylinder-Based Tree Trunk Detection in LiDAR Point Clouds for Forestry Applications by Shaobo Ma, Yongkang Chen, Zhefan Li, Junlin Chen, Xiaolan Zhong

Subjects: Get full text

Cooperative spectrum sensing algorithm based on limiting eigenvalue distribution by Yin MI, Guang-yue LU

Subjects: Get full text

An improved SMOTE algorithm for enhanced imbalanced data classification by expanding sample generation space by Ying Li, Yali Yang, Peihua Song, Lian Duan, Rui Ren

“…Then the Euclidean distance between the two samples is multiplied by a random number to generate a random quantity. …”
Get full text

Determining the Number of Measurements and Bootstrap Samples Required to Estimate of Long-Term Noise Indicators by Bartłomiej STĘPIEŃ

“…The maximum size of original random sample should not exceed n = 50 elements. The minimum number of bootstrap replications necessary for estimation should be B = 5000. …”
Get full text

Orderings of the second-largest order statistic with modified proportional reversed hazard rate samples by Mingxia Yang

“…Next, the paper addressed the reversed hazard rate order relationship for the second- largest order statistic between two groups of independent heterogeneous random variables. This analysis was conducted under various conditions: the same tilt parameters with different proportional reversed hazard rate parameters, different tilt parameters with the same proportional reversed hazard rate parameters, and different sample sizes with the same parameters. …”
Get full text

On the Efficient Generation of α-κ-μ and α-η-μ White Samples with Applications by Rausley Adriano Amaral de Souza, Antonio Marcelo Oliveira Ribeiro, Dayan Adionel Guimarães

Get full text

Post-hoc Evaluation of Sample Size in a Regional Digital Soil Mapping Project by Daniel D. Saurette, Richard J. Heck, Adam W. Gillespie, Aaron A. Berg, Asim Biswas

“…Using a regional soil survey dataset with 1791 sampled and described soil profiles, we first extracted an external validation dataset using the conditioned Latin hypercube sampling (cLHS) algorithm and then created repeated (<i>n</i> = 10) sample plans of increasing size from the remaining calibration sites using the cLHS, feature space coverage sampling (FSCS), and simple random sampling (SRS). …”
Get full text

Self-supervised speech representation learning based on positive sample comparison and masking reconstruction by Wenlin ZHANG, Xuepeng LIU, Tong NIU, Qi CHEN, Dan QU

“…To solve the problem that existing contrastive prediction based self-supervised speech representation learning methods need to construct a large number of negative samples, and their performance depends on large training batches, requiring a lot of computing resources, a new speech representation learning method based on contrastive learning using only positive samples was proposed.Combined with reconstruction loss, the proposed method could obtain better representation with lower training cost.The proposed method was inspired by the idea of the SimSiam method in image self-supervised representation learning.Using the siamese network architecture, two random augmentations of the input speech signals were processed by the same encoder network, then a feed-forward network was applied on one side, and a stop-gradient operation was applied on the other side.The model was trained to maximize the similarity between two sides.During training processing, negative samples were not required, so small batch size could be used and training efficiency was improved.Experimental results show that the representation model obtained by the new method achieves or exceeds the performance of existing mainstream speech representation learning models in multiple downstream tasks.…”
Get full text

Self-supervised speech representation learning based on positive sample comparison and masking reconstruction by Wenlin ZHANG, Xuepeng LIU, Tong NIU, Qi CHEN, Dan QU

“…To solve the problem that existing contrastive prediction based self-supervised speech representation learning methods need to construct a large number of negative samples, and their performance depends on large training batches, requiring a lot of computing resources, a new speech representation learning method based on contrastive learning using only positive samples was proposed.Combined with reconstruction loss, the proposed method could obtain better representation with lower training cost.The proposed method was inspired by the idea of the SimSiam method in image self-supervised representation learning.Using the siamese network architecture, two random augmentations of the input speech signals were processed by the same encoder network, then a feed-forward network was applied on one side, and a stop-gradient operation was applied on the other side.The model was trained to maximize the similarity between two sides.During training processing, negative samples were not required, so small batch size could be used and training efficiency was improved.Experimental results show that the representation model obtained by the new method achieves or exceeds the performance of existing mainstream speech representation learning models in multiple downstream tasks.…”
Get full text

Ultra-Low Sampled and High Precision TDLAS Thermometry Via Artificial Neural Network by Heng Xie, Lijun Xu, Yutian Tan, Guangyu Hou, Zhang Cao

“…Water vapor temperatures in a heating device were measured by ultra-low sampled and high-precision tunable diode laser spectroscopy (TDLAS) Bichromatic distributed feedback (DFB) lasers were used as light sources. …”
Get full text

Coupled memory sampled-data control for fractional stochastic wind energy conversion models by Girija Panneerselvam, Prakash Mani

“…This study aims to design a coupled memory sampled-data control (CMSDC) for fractional stochastic wind energy conversion systems (WECSs). …”
Get full text

Comparative analysis of the performance of selected machine learning algorithms depending on the size of the training sample by Kupidura Przemysław, Kępa Agnieszka, Krawczyk Piotr

“…Each variant was classified multiple (20) times, using training samples of different sizes: from 100 pixels to 200,000 pixels. …”
Get full text

Using Constrained K-Means Clustering for Soil Texture Mapping with Limited Soil Samples by Fubin Zhu, Changda Zhu, Zihan Fang, Wenhao Lu, Jianjun Pan

“…However, these methods may not yield optimal predictive performance due to the limited number of soil samples. Therefore, we propose using Constrained K-Means Clustering to combine a small number of labeled samples with a large amount of unlabeled data, thereby achieving improved prediction in soil texture mapping. …”
Get full text

Corrigendum to “Effectiveness of chemical inactivation of infectious liquid biological waste: A randomized sample study of research laboratories in Switzerland” [J.... by Alina C. Teuscher, Charlotte Ruhnau, Nicole Stöcklin, Fabienne Wichmann, Evelyn Ilg Hampe, Claudia Bagutti

Get full text

Occurrence, sampling, identification and characterization of microplastics in tap water: A systematic review and meta-analysis by Masoumeh Malekzadeh, Reza Dehghanzadeh, Seyedeh Masoumeh Ebrahimi, Parvin Sarbakhsh, Zahra Fathifar, Hassan Aslani

“…All techniques used for sampling, processing, and analyzing MPs in tap water were also assessed. …”
Get full text

Optimal surveillance against foot-and-mouth disease: A sample average approximation approach. by Tom Kompas, Pham Van Ha, Hoa-Thi-Minh Nguyen, Graeme Garner, Sharon Roche, Iain East

“…This paper focuses on the case of finding the optimal level of surveillance against a highly infectious animal disease where time, space and randomness are fully considered. We apply the Sample Average Approximation approach to solve our problem, and to control model dimension, we propose the use of an infection tree model, in combination with sensible 'tree-pruning' and parallel processing techniques. …”
Get full text

Willingness of population health survey participants to provide personal health information and biological samples by Harpreet Jaswal, Anca Ialomiteanu, Hayley Hamilton, Jürgen Rehm, Samantha Wells, Kevin D. Shield

“…Question order effects were tested using a randomized trial. Results The proportion of respondents willing to provide blood samples, saliva samples, probabilistic linkage, and direct linkage with personal health information were 19.9%, 36.2%, 82.1%, and 17%, respectively. …”
Get full text

Depression in older adults: prevalence and risk factors in a primary health care sample by Uschenka Padayachey, S Ramlall, J Chipps

“…Descriptive statistics were used to summarise the sample demographics and response rate and non-parametric statistics were used to test for associations and differences. …”
Get full text