A typical BCI system depicting the flow and processing of EEG data. حسب Gursimran Singh (575288)

الموضوعات:

Contrast enhancement of digital images using dragonfly algorithm حسب Soumyajit Saha (19726163)

"…Comparisons with state-of-art methods ensure the superiority of the proposed algorithm. The Python implementation of the proposed approach is available in this <a href="https://github.com/somnath796/DA_contrast_enhancement" target="_blank">Github repository</a>.…"

Example of a typical workflow to construct a network using NeKo. حسب Marco Ruscone (11747264)

Comparative analysis of WordNet replacement impact on data distribution. حسب Enock Niyonkuru (21246879)

LBQANA python code + Merged Gene Expression Dataset from GSE10810, GSE17907, GSE20711, GSE42568, GSE45827, and GSE61304 for Breast Cancer Biomarker Discovery حسب M RN (9866504)

Dataset of networks used in assessing the Troika algorithm for clique partitioning and community detection حسب Samin Aref (4683934)

"…Each network is provided in .gml format or .pkl format which can be read into a networkX graph object using standard functions from the networkX library in Python. For accessing other networks used in the study, please refer to the article for references to the primary sources of those network data.…"

Overnight technician routing and scheduling problem with time windows and balanced workloads: a bi-objective zebra optimization algorithm حسب Abolfazl Gharaei (21803416)

"…The performance evaluation and validation results revealed that the proposed ML-based BOZOA provides very good performance in solving TRSPTWs at a variety of scales with respect to the optimality criteria, including, number of taken iterations, infeasibility, optimality error and complementarity compared with both an exact solver and two inspired algorithms from ZOA.</p> <p><b>Highlights</b></p><p>An ML-based bi-objective zebra optimisation algorithm to treat large-scale TRSPs</p><p>Centroid-based clustering on the population of zebras to avoid bias towards a specific search space</p><p>Making a trade-off between exploration and exploitation of the feasible region in the developed algorithm</p><p>A new MINLP model of a weighted bi-objective TRSP with limited capacity depots</p><p>Workload function, penalty function for lateness, subcontracts, time windows for tasks and breaks</p><p>Experiments using real data to show the performance of the model and solution method</p><p></p> <p>An ML-based bi-objective zebra optimisation algorithm to treat large-scale TRSPs</p> <p>Centroid-based clustering on the population of zebras to avoid bias towards a specific search space</p> <p>Making a trade-off between exploration and exploitation of the feasible region in the developed algorithm</p> <p>A new MINLP model of a weighted bi-objective TRSP with limited capacity depots</p> <p>Workload function, penalty function for lateness, subcontracts, time windows for tasks and breaks</p> <p>Experiments using real data to show the performance of the model and solution method</p>…"

Summary of related works. حسب Yiming Kuang (22120458)

"…PiCCL is simple and light weight, it does not use asymmetric networks, intricate pretext tasks, hard to compute loss functions or multimodal data, which are common for multiview contrastive learning frameworks and could hinder performance, simplicity, generalizability and explainability. …"

Results on STL-10 at 500 epoch. حسب Yiming Kuang (22120458)

"…PiCCL is simple and light weight, it does not use asymmetric networks, intricate pretext tasks, hard to compute loss functions or multimodal data, which are common for multiview contrastive learning frameworks and could hinder performance, simplicity, generalizability and explainability. …"

Results on CIFAR-10 & CIFAR-100. حسب Yiming Kuang (22120458)

"…PiCCL is simple and light weight, it does not use asymmetric networks, intricate pretext tasks, hard to compute loss functions or multimodal data, which are common for multiview contrastive learning frameworks and could hinder performance, simplicity, generalizability and explainability. …"

Speed and Memory Metrics. حسب Yiming Kuang (22120458)

"…PiCCL is simple and light weight, it does not use asymmetric networks, intricate pretext tasks, hard to compute loss functions or multimodal data, which are common for multiview contrastive learning frameworks and could hinder performance, simplicity, generalizability and explainability. …"

Image augmentation methods. حسب Yiming Kuang (22120458)

"…PiCCL is simple and light weight, it does not use asymmetric networks, intricate pretext tasks, hard to compute loss functions or multimodal data, which are common for multiview contrastive learning frameworks and could hinder performance, simplicity, generalizability and explainability. …"

Results on STL-10 with batch size = 256. حسب Yiming Kuang (22120458)

"…PiCCL is simple and light weight, it does not use asymmetric networks, intricate pretext tasks, hard to compute loss functions or multimodal data, which are common for multiview contrastive learning frameworks and could hinder performance, simplicity, generalizability and explainability. …"

Supervised Predictive Modeling of High-dimensional Data with Group l0-norm Constrained Neural Networks حسب Zhihuang Yang (22530437)

"…Moreover, two iterative greedy selection algorithms, which iterate between a standard gradient descent step and a hard thresholding step with or without debiasing, are presented to implement the computation. …"

Supplementary file 1_Hamiltonian formulations of centroid-based clustering.pdf حسب Myeonghwan Seong (21159605)

"…However, defining similarity is often ambiguous, making it challenging to determine the most appropriate objective function for a given dataset. Traditional clustering methods, such as the k-means algorithm and weighted maximum k-cut, focus on specific objectives—typically relying on average or pairwise characteristics of the data—leading to performance that is highly data-dependent. …"

Global Aridity Index and Potential Evapotranspiration (ET0) Database: Version 3.1 حسب Robert Zomer (12796235)

GridScopeRodents: High-Resolution Global Typical Rodents Distribution Projections from 2021 to 2100 under Diverse SSP-RCP Scenarios حسب Yang Lan (20927512)

"…Using occurrence data and environmental variable, we employ the Maximum Entropy (MaxEnt) algorithm within the species distribution modeling (SDM) framework to estimate occurrence probability at a spatial resolution of 1/12° (~10 km). …"

SpatialKNifeY analysis landscape. حسب Shunsuke A. Sakai (13789939)

Data for "A multi-objective platform for autonomous property targeting and optimization of colloidal lead halide perovskite quantum dots" حسب Neal Munyebvu (19690954)

Hippocampal and cortical activity reflect early hyperexcitability in an Alzheimer's mouse model حسب Marina Diachenko (19739092)

"…</p><p dir="ltr">All data are available upon request. The standalone Python implementation of the fE/I algorithm is available under a CC-BY-NC-SA license at <a href="https://github.com/arthur-ervin/crosci" target="_blank">https://github.com/arthur-ervin/crosci</a>. …"