A Fast kNN Algorithm Using Multiple Space-Filling Curves

Barkalov, Konstantin; Shtanyuk, Anton; Sysoyev, Alexander

doi:10.3390/e24060767

Cited by 10 publications

(5 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Given the multidimensional characteristics among the variables, we first used Pearson's heat map to observe the correlation among the variables and used the t-test method for data downscaling [20]. Three ML models -XGBoost, SGD, and KNN were used to develop predictive models [21][22][23][24][25]. The downscaled data is fed into a subsequent ML model.…”

Section: Discussionmentioning

confidence: 99%

The Value of the Gensini Score For Prognostic Assessment in Patients with Acute Coronary Syndrome--A Retrospective Cohort Study Based on Machine Learning Methods

Chen,

Jia,

Mou

et al. 2023

Preprint

View full text Add to dashboard Cite

Background The Gensini score (GS) provides a good assessment of the degree of coronary plate loading. However, its clinical significance has been little explored. Methods In this retrospective cohort study, we implemented model development and performance comparison on database of The Fourth Affiliated Hospital of Zhejiang University School of Medicine (2019.1-2020.12). The patients were followed up for 2 years. Follow-up endpoint was the occurrence of MACCEs. We extracted clinical baseline data from each ACS patient within 24 hours of hospital admission and randomly divided the datasets into 70% for model training and 30% for model validation. Area under the curve (AUC) was used to compare the prediction performance of XGBoost, SGD and KNN. A decision tree model was constructed to predict the probability of MACCEs using a combination of weight features picked by XGBoost and clinical significance. Results A total of 361 ACS patients who met the study criteria were included in this study. It could be observed that the probability of a recurrent MACCEs within 2 years was 25.2%. XGboost had the best predictive efficacy (AUC:0.97). GS has high clinical significance. Then we used GS, Age and CK-MB to construct a decision tree model to predict the probability model of MACCEs reoccurring, and the final AUC value reached 0.771. Conclusions GS is a powerful indicator for assessing the prognosis of patients with ACS. The cut-off value of GS in the decision tree model provides a reference standard for grading the risk level of patients with ACS.

show abstract

Section: Discussionmentioning

confidence: 99%

The Value of the Gensini Score For Prognostic Assessment in Patients with Acute Coronary Syndrome--A Retrospective Cohort Study Based on Machine Learning Methods

Chen,

Jia,

Mou

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…In this study, we used a uniform sampling method to select m center points c i ∈ R 3 from point cloud Y. For each center point c i , we used the k-nearest-neighbor (k-NN) [49] algorithm to identify k-nearest-neighbor points in terms of Euclidean distance. A patch v i is a set of points that is composed of one center point c i and k nearest neighbors.…”

Section: Constructing a Graph Based On Self-similarity Theorymentioning

confidence: 99%

A Color- and Geometric-Feature-Based Approach for Denoising Three-Dimensional Cultural Relic Point Clouds

Gao,

Wang,

Zhao

2024

Entropy

View full text Add to dashboard Cite

In the acquisition process of 3D cultural relics, it is common to encounter noise. To facilitate the generation of high-quality 3D models, we propose an approach based on graph signal processing that combines color and geometric features to denoise the point cloud. We divide the 3D point cloud into patches based on self-similarity theory and create an appropriate underlying graph with a Markov property. The features of the vertices in the graph are represented using 3D coordinates, normal vectors, and color. We formulate the point cloud denoising problem as a maximum a posteriori (MAP) estimation problem and use a graph Laplacian regularization (GLR) prior to identifying the most probable noise-free point cloud. In the denoising process, we moderately simplify the 3D point to reduce the running time of the denoising algorithm. The experimental results demonstrate that our proposed approach outperforms five competing methods in both subjective and objective assessments. It requires fewer iterations and exhibits strong robustness, effectively removing noise from the surface of cultural relic point clouds while preserving fine-scale 3D features such as texture and ornamentation. This results in more realistic 3D representations of cultural relics.

show abstract

“…[36] Quezada et al proposed a KNN algorithm based on quantum sorting, which is suitable for quantum computers with limited circuit depth and meets the requirements of adaptability. [37] The speeds of all the above QKNN algorithms are faster than those of the traditional KNN algorithm. However, these algorithms have obtained better performance typically at the cost of classification accuracy.…”

Section: Introductionmentioning

confidence: 99%

Quantum K‐Nearest Neighbor Classification Algorithm via a Divide‐and‐Conquer Strategy

Gong,

Ding,

et al. 2024

Adv Quantum Tech

View full text Add to dashboard Cite

The K‐nearest neighbor algorithm is one of the most frequently applied supervised machine learning algorithms. Similarity computing is considered to be the most crucial and time‐consuming step among the classical K‐nearest neighbor algorithm. A quantum K‐nearest neighbor algorithm is proposed based on the divide‐and‐conquer strategy. A quantum circuit is designed to calculate the fidelity between the test sample and each feature vector of the training dataset. The quantum K‐nearest neighbor algorithm has higher classification efficiency in high‐dimensional data processing. The classification accuracy of the proposed algorithm is equivalent to that of the classical K‐nearest neighbor algorithm under the IRIS dataset. In addition, compared with the typical quantum K‐nearest neighbor algorithms, the proposed classification method possesses higher classification accuracy with less calculation time, which has wide applications in the industrial field.

show abstract

A Fast kNN Algorithm Using Multiple Space-Filling Curves

Cited by 10 publications

References 24 publications

The Value of the Gensini Score For Prognostic Assessment in Patients with Acute Coronary Syndrome--A Retrospective Cohort Study Based on Machine Learning Methods

The Value of the Gensini Score For Prognostic Assessment in Patients with Acute Coronary Syndrome--A Retrospective Cohort Study Based on Machine Learning Methods

A Color- and Geometric-Feature-Based Approach for Denoising Three-Dimensional Cultural Relic Point Clouds

Quantum K‐Nearest Neighbor Classification Algorithm via a Divide‐and‐Conquer Strategy

Contact Info

Product

Resources

About