Efficient medoid-based Silhouette method speeds up clustering evaluation.
problem Difficulty in evaluating clustering results due to many measures and data set dependence.
method Direct optimization of medoid-based Silhouette, combining PAM algorithm improvements.
result 10464x speedup in clustering evaluation for large datasets.
A new medoid-based Silhouette method selects optimal cluster numbers efficiently.
problem Difficulty in evaluating clustering results and choosing the right number of clusters.
method Developed a medoid-based Silhouette variant, analyzed its properties, and provided fast optimization methods.
result A 10464x speedup in choosing optimal cluster numbers compared to original PAMMEDSIL.
In this work, we introduce a deep-structured conditional random field (DS-CRF) model for the purpose of state-based object silhouette tracking. The proposed DS-CRF model consists of a series of state layers, where each state layer spatially characterizes the object silhouette at a particular point in time. The interact…
Visualizes classification accuracy and label bias in neural nets and trees.
problem Identifying mislabeled cases in neural net and tree-based classifications.
method Silhouette plots and quasi residual plots of PAC (probability of alternative class).
result Comparison of different classifications using silhouette width and PAC plots.
Smooth generative model of shapes with uncertainty from silhouette images.
problem Challenges in modeling shapes represented as silhouette images due to intractable posteriors.
method Gaussian Process Deep Belief Networks (GPDBN) that learn from small data and propagate uncertainty.
result Proposed model provides favorable results compared to state-of-the-art models.
New clustering algorithms optimize Average Silhouette Width for better cluster quality.
problem Optimizing clustering using Average Silhouette Width (ASW).
method Proposed two algorithms: OSil and FOSil, compared with existing methods.
result New methods prove useful and sensible in many cases, but with some weaknesses.
Study uses CNNs to estimate BMI from photos.
problem Estimating BMI from photos with limited data.
method Used deep learning (CNNs) to process silhouette images.
result High correlation between estimated and actual BMI.
New method estimates causal effects in complex spaces using topological structures.
problem Challenges in estimating causal effects in non-Euclidean spaces.
method Developed a topological causal inference framework using power-weighted silhouette functions of persistence diagrams.
result Successfully quantifies topological treatment effects across various complex outcomes.
TDA improves FX clustering quality over traditional methods.
problem Capturing complex currency co-movements in FX markets.
method Topological Data Analysis (TDA) compared to traditional statistical methods on monthly FX returns.
result TDA-based clustering yields more compact and well-separated clusters.
OSil algorithm optimizes clustering quality using ASW.
problem Optimizing clustering quality using ASW.
method Distance-based objective function optimizing ASW for clustering.
result OSil algorithm outperforms other clustering methods in clustering quality.
The paper challenges the validity of cluster validity measures in unsupervised learning.
problem The validity of cluster validity measures in selecting optimal clusterings.
method The authors investigate the use of cluster validity measures as objective functions in unsupervised learning and introduce a new variant of the Dunn index.
result Many cluster validity measures promote clusterings that do not match expert knowledge well.
Paper defends against malware detection attacks using clustering and deep learning.
problem Label flipping attacks on malware detection systems in IoT environments.
method Developed a Silhouette clustering-based attack mechanism and two CNN-type deep learning algorithms for defense.
result Proposed algorithms LSD and CSD improve malware detection accuracy by up to 19%.
The paper investigates how irrelevant features affect clustering performance.
problem The challenge of identifying relevant features in unsupervised clustering tasks.
method Investigation of clustering performance with added irrelevant features.
result Different types of irrelevant features impact clustering outcomes differently.
A new method clusters malware data more effectively.
problem Difficult clustering of drive-by-download malware data.
method Iterative data rescaling method to enhance cluster separation.
result Improved separation between malware clusters, higher silhouette width.
The paper extends cluster validity indices for incremental analysis.
problem Providing incremental alternatives for cluster validation.
method Extending iCVI family to include 6 incremental indices and examining their behavior under under- and over-partitioning.
result Over-partitioning is more challenging to detect than under-partitioning.
Generative model creates realistic images with 3D understanding.
problem Lack of 3D understanding in existing image generation models.
method Disentangled 3D representation using shape, viewpoint, and texture.
result Generates more realistic images and enables 3D operations.
Proposes DISCO, the first CVI for density-based clustering with noise.
problem Evaluation of noise assignments in density-based clustering.
method Density-connectivity and Silhouette Coefficient adaptation for noise evaluation.
result DISCO is the first CVI to explicitly assess noise assignments.
Equal-volume polygons are obtained from adequate discretizations of curves in 3-space, contained or not in surfaces. In this paper we explore the similarities of these polygons with the affine arc-length parameterized smooth curves to develop a theory of discrete affine invariants. Besides obtaining discrete affine inv…
A novel resampling technique addresses class imbalance in imbalanced datasets.
problem Class imbalance in real-world datasets, especially in rare event detection.
method Developed two oversampling algorithms: G1Nos 1-Nearest Neighbour.
result Our oversampling algorithms outperform state-of-the-art methods in all metrics.
Study clusters bank customers using LSTM and DTW.
problem Efficiently segmenting bank customers for targeted offers.
method Encoder-decoder LSTM network and Dynamic Time Warping (DTW).
result Hybrid method yields more accurate clusters.
Aerial robot estimates human pose and path using dynamic classifier selection.
problem Estimating human pose and trajectory from aerial video.
method Dynamic classifier selection architecture; perspective correction; HOG and CNN features; 64 pose-viewpoint classes.
result Dynamic classifier selection improves efficiency and accuracy.
New k-means method handles random data better than traditional techniques.
problem Limitations of traditional clustering methods in random data.
method Probabilistic metric space with random normed k-means (RNKM).
result RNKM outperforms traditional methods in complex clustering scenarios.
Enhances curve alignment for diverse data types.
problem Aligning curve data effectively.
method Developed nonlinear transformations for curve data.
result Successfully aligned synthetic and real curve data.
Probabilistic models with discrete latent variables naturally capture datasets composed of discrete classes. However, they are difficult to train efficiently, since backpropagation through discrete variables is generally not possible. We present a novel method to train a class of probabilistic models with discrete late…
New metric improves clustering in persistent homology.
problem Improving clustering accuracy in persistent homology.
method Defined a new non-archimedean cophenetic metric.
result Cophenetic metric enhances clustering quality and inter-relations.
In this paper we introduce three methods for re-scaling data sets aiming at improving the likelihood of clustering validity indexes to return the true number of spherical Gaussian clusters with additional noise features. Our method obtains feature re-scaling factors taking into account the structure of a given data set…
Probabilistic principal component analysis (PPCA) seeks a low dimensional representation of a data set in the presence of independent spherical Gaussian noise, Sigma = (sigma^2)*I. The maximum likelihood solution for the model is an eigenvalue problem on the sample covariance matrix. In this paper we consider the situa…
A new clustering evaluation index based on density estimation.
problem Improving internal clustering evaluation indices.
method The index is a mixture of Ambiguous and Similarity sub-indices, calculated using density estimation.
result The new index significantly outperforms other internal clustering evaluation indices.
Recently we proposed a general, ensemble-based feature engineering wrapper (FEW) that was paired with a number of machine learning methods to solve regression problems. Here, we adapt FEW for supervised classification and perform a thorough analysis of fitness and survival methods within this framework. Our tests demon…
Representation learning seeks to expose certain aspects of observed data in a learned representation that's amenable to downstream tasks like classification. For instance, a good representation for 2D images might be one that describes only global structure and discards information about detailed texture. In this paper…
Many different methods to train deep generative models have been introduced in the past. In this paper, we propose to extend the variational auto-encoder (VAE) framework with a new type of prior which we call "Variational Mixture of Posteriors" prior, or VampPrior for short. The VampPrior consists of a mixture distribu…
We present a layered Boltzmann machine (BM) that can better exploit the advantages of a distributed representation. It is widely believed that deep BMs (DBMs) have far greater representational power than its shallow counterpart, restricted Boltzmann machines (RBMs). However, this expectation on the supremacy of DBMs ov…
The segmentation of the left ventricle (LV) from CINE MRI images is essential to infer important clinical parameters. Typically, machine learning algorithms for automated LV segmentation use annotated contours from only two cardiac phases, diastole, and systole. In this work, we present an analysis work-flow for fully-…
HD-BWDM improves clustering validation in high-dimensional data.
problem Determining the right number of clusters in high-dimensional data.
method HD-BWDM integrates random projection, PCA, trimmed clustering, and medoid-based distances.
result HD-BWDM remains stable and interpretable under high-dimensional projections and contamination.
New index improves anomaly detection in correlated time series data.
problem Challenges in evaluating cluster quality for anomaly detection.
method Introduced Synchronized Anomaly Agreement Index (SAAI) to assess cluster quality.
result Maximizing SAAI improves anomaly detection accuracy by 0.23 compared to SSC and by 0.32 compared to X-Means.
This paper evaluates and validates cluster results using external and internal evaluation methods.
problem Evaluating and validating the quality of clustering results.
method External evaluation using Homogeneity, Correctness, and V-measure scores; internal evaluation using Silhouette Index and Sum of Square Errors.
result Validation of the number of clusters using dendrogram and statistical frequency distribution.
Extends Fisher's Discriminant Analysis for interval-valued data.
problem Classifying entities represented by intervals and histograms.
method Adapts Fisher's Discriminant Analysis using Moore's interval arithmetic and Mallows' distance.
result Discriminant directions for interval-valued data are numerically maximized.
A new method steers Gaussian distributions with minimal effort.
problem Steering high-dimensional Gaussian distributions efficiently.
method Sliced feedback controller using one-dimensional projections and averaging.
result The method steers Gaussian distributions to targets efficiently.
This work proposes a method to integrate algorithms into neural networks using continuous relaxation.
problem Training neural networks with new forms of supervision like ordering constraints.
method Relaxing discrete conditions in control structures like conditional statements, loops, and indexing to make them differentiable.
result The proposed method can keep up with relaxations designed for specific tasks, showing general applicability.
Understanding and reasoning about places and their relationships are critical for many applications. Places are traditionally curated by a small group of people as place gazetteers and are represented by an ID with spatial extent, category, and other descriptions. However, a place context is described to a large extent…
The infinite restricted Boltzmann machine (iRBM) is an extension of the classic RBM. It enjoys a good property of automatically deciding the size of the hidden layer according to specific training data. With sufficient training, the iRBM can achieve a competitive performance with that of the classic RBM. However, the c…
CARVE validates clustering results using resampling and stability analysis.
problem Inconsistent and unreliable clustering results due to algorithm, preprocessing, and k sensitivity. method CARVE uses resampling-based validation and stability analysis to evaluate multiple clustering algorithms and hyperparameters.
result CARVE consistently recovers near-optimal clusterings and finer biological structure.
Enhances clustering quality evaluation in noisy data.
problem Reliable clustering quality assessment in noisy Gaussian mixtures.
method Feature Importance Rescaling (FIR) method.
result FIR improves correlation between cluster validity indices and ground truth.
Clust-PSI-PFL uses PSI to improve accuracy and fairness in federated learning.
problem Non-IID data biases federated learning performance.
method Clust-PSI-PFL uses clustering and PSI to form homogeneous groups of clients.
result Clust-PSI-PFL delivers up to 18% higher global accuracy and improves client fairness.
Pix2Shape learns 3D scene representations from single images without supervision.
problem Learning 3D scene information from a single image without supervision.
method Pix2Shape uses an encoder, decoder, and critic network to generate 2.5D surfel-based reconstructions.
result Pix2Shape can generate complex 3D scenes from a single image, scaling with on-screen resolution.
reval package selects best clustering solutions via stability-based validation.
problem Challenges in determining best clustering solutions due to lack of validation methods.
method Stability-based relative clustering validation methods.
result Determines best clustering solutions that generalize to unseen data.
Paper proposes a new descriptor for early trajectory characterization in matrix iterations.
problem Comparing early behavior of high-dimensional trajectories in nonlinear matrix iterations.
method Develops a two-channel fuzzy coordinate system using F-transform for compact representation.
result The descriptor achieves high R^2 values (mean = 0.6480) in approximating convergence lengths.
New clustering method improves climate data analysis in Lesser Antilles.
problem Inducing undesirable effects in clustering algorithms using Euclidean distance.
method Replacing Euclidean distance with Expert Deviation (ED) based on symmetrized Kullback-Leibler divergence.
result KMS-ED produces more interpretable clusters with better discrimination of daily situations.