Distance-based clustering methods categorize samples by optimizing a global criterion, finding ellipsoid clusters with roughly equal sizes. In contrast, density-based clustering techniques form clusters with arbitrary shapes and sizes by optimizing a local criterion. Most of these methods have several hyper-parameters, and their performance is highly dependent on the hyper-parameter setup. Recently, a Gaussian Density Distance (GDD) approach was proposed to optimize local criteria in terms of distance and density properties of samples. GDD can find clusters with different shapes and sizes without any free parameters. However, it may fail to discover the appropriate clusters due to the interfering of clustered samples in estimating the density and distance properties of remaining unclustered samples. Here, we introduce ADAPTIVE GDD (AGDD), which eliminates the inappropriate effect of clustered samples by ADAPTIVEly updating the parameters during clustering. It is stable and can identify clusters with various shapes, sizes, and densities without adding extra parameters. The distance metrics calculating the dissimilarity between samples can affect the clustering performance. The effect of different distance measurements is also analyzed on the method. The experimental results conducted on several well-known datasets show the effectiveness of the proposed AGDD method compared to the other well-known clustering methods.

The aim of this article is to select material for the components of the quadrotor drones with a time-variable structure. Although the use of a time-variable structure provides the capability to maneuver along various paths and exhibit diverse functionalities, dimensional changes may lead to component failures due to loads, vertical forces, and drag forces from the motors. Therefore, in the design process, in addition to considering weight and cost, parameters related to the durability and load-bearing capacity of the robot's structure must be examined. There are various criteria for selecting suitable materials for construction, and in this regard, the effectiveness of each criterion is specified in the design tables. Ultimately, the optimal materials for use are identified. The results indicate that by selecting Aluminum 7075-T6 and ABS+ Filament materials, the deformation of the drone's body under maximum motor loads is minimal, and the factors of weight and total cost are also optimized.

Steganalysis is an interesting classi cation problem to discriminate the images, including hidden messages from the clean ones. There are many methods, including deep CNN networks, to extract  ne features for this classi cation task. Also, some researches have been conducted to improve the  nal classi er. Some state-of-the-art methods use ensemble of networks by a voting strategy to achieve more stable performance. In this paper, a SELECTION phase is proposed to  lter improper networks before any voting. This  ltering is done by a binary relevance multi-label classi cation approach. Xu-Net and ResT-Net, the most famous state-of-the-art Steganalysis ensemble models, are considered as the base networks for feature extraction. The Logistic Regression (LR) is chosen here as the last layer of the networks for classi cation. One large-margin Fisher's linear discriminant (FLD) classi er is trained for each one of the networks to measure its suitability in classifying the query image. The proposed method with di erent approaches is applied on the BOSSbase dataset and compared to traditional voting and some state-of-the-art related ensemble techniques. The results show signi cant accuracy improvement of the proposed method in comparison with others.

We consider the problem of using simulation to efficiently estimate the win probabilities for participants in a general random knockout TOURNAMENT. Both of our proposed estimators, one based on the notion of “observed survivals” and the other based on conditional expectation and post-stratification, are highly effective in terms of variance reduction when compared to the raw simulation estimator. For the special case of a classical 2n -player random knockout TOURNAMENT, where each survivor of the previous round plays in the current round, a second conditional expectation based estimator is introduced. At the end, we compare our proposed simulation estimators based on a numerical example and in terms of both variance reduction and the time to complete the simulation experiment. Based on our empirical study, the method of “observed survivals” is the most efficient method.

Local smoothness and nonlocal self-similarity of natural images are two main priors in single image super resolution (SISR) problem. Although local sparsity is efficiently utilized to describe the local smoothness, but ignoring the correlation between the sparse representation coefficients of similar patches can lead to inaccurate sparse coding coefficients. In this paper, we propose the method that enforce the local smoothness and nonlocal self-similarity by sparse representation in a unified framework, called ADAPTIVE group-based sparse domain SELECTION (A-GSDS). Nonlocal patches with similar structures are exploited and stacked in the form of matrix as the basic unit of sparse representation called group. These groups are converted into a column vector, each column selects the best fitted PCA sub dictionary which is learned from the training data. The sparse coding process for each column in the domain of group leads to find sparse vectors which can be easily estimated by the selected orthogonal sub dictionaries. To further improve the performance of the group-based sparse representation, we use nonlocal means regularization term. Extensive experimental results validate the effectiveness of the proposed method comparing with the state-of-the-art algorithms.