Showing papers on "Centroid published in 2022"

Enhancement of Energy Efficiency and Network Lifetime Using Modified MPCT Algorithm in Wireless Sensor Networks

Abstract: Wireless sensor networks (WSN) allude to gathering of spatially fragmented and committed sensors for observing and documenting various physical and climatic variables like temperature, moistness and, so on. WSN is quickly growing its work in different fields like clinical, enterprises, climate following and so on. However, the sensor nodes have restricted battery life and substitution or re-energizing of these batteries in the sensor nodes is exceptionally troublesome for the most parts. Energy effectiveness is the significant worry in the remote sensor networks as it is significant for keeping up its activity. In this paper, clustering algorithms based on sensor module energy states to strengthen the network longevity of wireless sensor networks is proposed (i.e. modified MPCT algorithm) in which cluster head determination depends on the every cluster power centroid as well as power of the sensor nodes. Correspondence between cluster leader and sink module employ a parameter distance edge for lessening energy utilization. The outcome got shows a normal increment of 60% in network lifetime compared to Low energy adaptive protocol, Energy efficient midpoint initialization algorithm (EECPK-means), Park K-means algorithm and Mobility path selection protocol.

Novel distance measures for intuitionistic fuzzy sets based on various triangle centers of isosceles triangular fuzzy numbers and their applications

Abstract: The paper aims at introducing novel distance measures for the intuitionistic fuzzy set (IFS) to discuss the decision-making problems. The current work exploits four different notions of centers, namely centroid, orthocenter, circumcenter and incenter of the triangle. First, we mold knowledge embedded in IFSs into isosceles TFN (triangular fuzzy number). Hence, based on these TFNs, we design four-novel distance/similarity measures for IFSs using the structures of the four aforementioned centers and inspect their properties. To avoid the loss of information during the conversion of IFSs into isosceles TFNs, we included the degree of hesitation (t) between the pairs of the membership function in the process. The compensations and authentication of the proposed measures are established with diverse counter-intuitive patterns and decision-making obstacles. Further, a clustering algorithm is also given to match the objects based on confidence levels. The performed analysis shows that the proposed measures give distinguishable and compatible results as contrasted to existing ones.

Centroid mutation-based Search and Rescue optimization algorithm for feature selection and classification

Abstract: Massive data is generated as a result of technological innovations in various fields. Medical data sets often have extremely complex dimensions with limited sample sizes. The researchers face a difficult problem in classifying this high-dimensional data. We present a novel optimization approach for better feature selection in medical data classification in this research. We call this approach a centroid mutation-based Search and Rescue optimization algorithm (cmSAR) based on a k-Nearest Neighbor (kNN) classifier for disease classification. The use of cmSAR in feature selection is to find the optimal group of features that show strong separability between two classes, solving premature convergence and improves the local search ability of the SAR algorithm. We use a fuzzy logic as a logical system, which is an extension of multi-valued logic to generate a fuzzy set and apply a centroid mutation operator on it. The statistical results of cmSAR were either identical or superior to those of well-known metaheuristic algorithms, including the Slime Mould Algorithm (SMA), Particle Swarm Optimization (PSO) algorithm, Sine Cosine Algorithm (SCA), Moth–Flame Optimization (MFO) algorithm, Whale Optimization Algorithm (WOA), Genetic Algorithm (GA), and the original SAR algorithm on 15 disease data sets with different feature sizes extracted from UCI. In addition, cmSAR outperformed the other algorithms in CEC-C06 2019 single-objective benchmark functions as well as in performance evaluation metrics for classification according to Friedman test and Bonferroni–Dunn test for statistical verification. The proposed cmSAR achieved superior performance on all the medical data sets.

C2FDA: Coarse-to-Fine Domain Adaptation for Traffic Object Detection

Abstract: Object detection in traffic scenes has attracted considerable attention from both academia and industry recently. Modern detectors achieve excellent performance under a simple constrained environment while performing poorly under the actual complex and open traffic environment. Therefore, the capability of adapting to new and unseen domains is a key factor for the large-scale application and proliferation of detectors in autonomous driving. To this end, this paper proposes a novel category-induced coarse-to-fine domain adaptation approach (C2FDA) for cross-domain object detection, which consists of three pivotal components: (1) Attention-induced coarse-grained alignment module (ACGA), which strengthens the distribution alignment across disparate domains within the foreground features in category-agnostic way by the minimax optimization between the domain classifier and the backbone feature extractor; (2) Attention-induced feature selection module, which assists the model to emphasize the crucial foreground features and enables the ACGA to focus on the relevant and discriminative foreground features, without being affected by the distribution of inconsequential background features; (3) Category-induced fine-grained alignment module (CFGA), which reduces the domain shift in category-aware way by minimizing the distance of centroids with the same category from different domains and maximizing that of centroids with disparate categories. We evaluate the performance of our approach in various source/target domain pairs and comprehensive results demonstrate that C2FDA significantly outperforms the state-of-the-art on multiple domain adaptation scenarios, i.e., the synthetic-to-real adaptation, the weather adaptation, and the cross camera adaptation.

A representation coefficient-based k-nearest centroid neighbor classifier

Abstract: K-nearest neighbor rule (KNN) has been regarded as one of the top 10 methods in the field of data mining. Due to its simplicity and effectiveness, it has been widely studied and applied to various classification tasks. In this article, we develop a novel representation coefficient-based k-nearest centroid neighbor method (RCKNCN), which aims to further improve the classification performance and reduce the method’s sensitivity to the neighborhood size k, especially in the cases of small sample size. Different from existing KNN-based methods, RCKNCN is able to capture both the proximity and the geometry of k-nearest neighbors, and learn to differentiate the contribution of each neighbor to the classification of a testing sample through a linear representation method. Moreover, under the RCKNCN framework, we also propose a novel weighted majority voting algorithm using the representation coefficients associated with individual nearest centroid neighbors, which are deemed to hold more discriminative information of the neighbors. To fully study the classification performance of RCKNCN, we compare it with the state-of-the-art KNN-based methods on many data sets that are widely used in the literature. The extensive experiments demonstrate the effectiveness and robustness of our method in various classification tasks.

PLAID: An Efficient Engine for Late Interaction Retrieval

Abstract: Pre-trained language models are increasingly important components across multiple information retrieval (IR) paradigms. Late interaction, introduced with the ColBERT model and recently refined in ColBERTv2, is a popular paradigm that holds state-of-the-art status across many benchmarks. To dramatically speed up the search latency of late interaction, we introduce the Performance-optimized Late Interaction Driver (PLAID) engine. Without impacting quality, PLAID swiftly eliminates low-scoring passages using a novel centroid interaction mechanism that treats every passage as a lightweight bag of centroids. PLAID uses centroid interaction as well as centroid pruning, a mechanism for sparsifying the bag of centroids, within a highly-optimized engine to reduce late interaction search latency by up to 7x on a GPU and 45x on a CPU against vanilla ColBERTv2, while continuing to deliver state-of-the-art retrieval quality. This allows the PLAID engine with ColBERTv2 to achieve latency of tens of milliseconds on a GPU and tens or just few hundreds of milliseconds on a CPU at large scale, even at the largest scales we evaluate with 140M passages.

Adaptive Active Positioning of Camellia oleifera Fruit Picking Points: Classical Image Processing and YOLOv7 Fusion Algorithm

Abstract: Camellia oleifera fruits are randomly distributed in an orchard, and the fruits are easily blocked or covered by leaves. In addition, the colors of leaves and fruits are alike, and flowers and fruits grow at the same time, presenting many ambiguities. The large shock force will cause flowers to fall and affect the yield. As a result, accurate positioning becomes a difficult problem for robot picking. Therefore, studying target recognition and localization of Camellia oleifera fruits in complex environments has many difficulties. In this paper, a fusion method of deep learning based on visual perception and image processing is proposed to adaptively and actively locate fruit recognition and picking points for Camellia oleifera fruits. First, to adapt to the target classification and recognition of complex scenes in the field, the parameters of the You Only Live Once v7 (YOLOv7) model were optimized and selected to achieve Camellia oleifera fruits’ detection and determine the center point of the fruit recognition frame. Then, image processing and a geometric algorithm are used to process the image, segment, and determine the morphology of the fruit, extract the centroid of the outline of Camellia oleifera fruit, and then analyze the position deviation of its centroid point and the center point in the YOLO recognition frame. The frontlighting, backlight, partial occlusion, and other test conditions for the perceptual recognition processing were validated with several experiments. The results demonstrate that the precision of YOLOv7 is close to that of YOLOv5s, and the mean average precision of YOLOv7 is higher than that of YOLOv5s. For some occluded Camellia oleifera fruits, the YOLOv7 algorithm is better than the YOLOv5s algorithm, which improves the detection accuracy of Camellia oleifera fruits. The contour of Camellia oleifera fruits can be extracted entirely via image processing. The average position deviation between the centroid point of the image extraction and the center point of the YOLO recognition frame is 2.86 pixels; thus, the center point of the YOLO recognition frame is approximately considered to be consistent with the centroid point of the image extraction.

Complementary moment detection for tracking a fast-moving object using dual single-pixel detectors.

Abstract: Target tracking has found important applications in particle tracking, vehicle navigation, aircraft monitoring, etc. However, employing single-pixel imaging techniques to track a fast-moving object with a high frame rate is still a challenge, due to the limitation of the modulation frequency of the spatial light modulator and the number of required patterns. Here we report a complementary single-pixel object tracking approach which requires only two geometric moment patterns to modulate the reflected light from a moving object in one frame. Using the complementary nature of a digital micromirror device (DMD), two identical single-pixel detectors are used to measure four intensities which can be used to acquire the values of zero-order and first-order geometric moments to track the centroid of a fast-moving object. We experimentally demonstrate that the proposed method successfully tracks a fast-moving object with a frame rate of up to 11.1 kHz in the first two experiments. In the third experiment, we compare previous works and find that the method can also accurately track a fast-moving object with a changing size and moving speed of 41.8 kilopixel/s on the image plane. The root mean squared errors in the transverse and axial directions are 0.3636 and 0.3640 pixels, respectively. The proposed method could be suitable for ultrafast target tracking.

Accurate Sensing of Power Transformer Faults From Dissolved Gas Data Using Random Forest Classifier Aided by Data Clustering Method

Abstract: In this paper, a novel approach for accurate sensing of incipient faults occurring in power transformers is proposed using dissolved gas analysis (DGA) technique. The Duval pentagon method is a popular technique often used to interpret faults occurring in a power transformer based on DGA data. However, one potential limitation of conventional Duval pentagon method is the presence of rigid fault boundaries within the pentagon which often lead to misinterpretations, leading to poor detection accuracy. Considering this issue, in this paper a modification of Duval pentagon method is proposed, where instead of using rigidly separated distinct fault zones, a density-based clustering (DBSCAN) approach is used to increase the resiliency and the accuracy of fault detection technique. At first, DBSCAN is used to form different fault clusters within the Duval pentagon. Following this, the centroid corresponding to each fault cluster within the Duval pentagon is determined. For accurate sensing of incipient transformer faults Euclidean distances between the respective centroids and the fault points of the input DGA data are proposed as new distinguishing features in this work. The proposed distance parameters combined with the relative gas concentration measures are finally served as input features to the random forest (RF) classifier, which returned very high classification accuracy. The performance of the RF classifier is also compared with three benchmark machine classifiers, all of which delivered acceptable results. The proposed method can be used for sensing of power transformer faults using Duval pentagon method with increased accuracy.

Multi-View K-Means Clustering With Adaptive Sparse Memberships and Weight Allocation

Abstract: Recently, many real-world applications exploit multi-view data, which is collected from diverse domains or obtained from various feature extractors and reflect different properties or distributions of the data. In this work, a novel unsupervised multi-view framework is proposed to cluster such data. The proposed method, called Multi-View clustering with Adaptive Sparse Memberships and Weight Allocation (MVASM), pays more attention to constructing a common membership matrix with proper sparseness over different views and learns the centroid matrix and its corresponding weight of each view. Concretely, MVASM method attempts to learn a common and flexible sparse membership matrix to indicate the clustering, which explores the underlying consensus information of multiple views, and solves the multiple centroid matrices and weights to utilize the view-specific information and further modifies the above-mentioned membership matrix. In addition, the theoretical analysis, including the determination of the power exponent parameter, convergence analysis, and complexity analysis are also presented. Compared to the state-of-the-art methods, the proposed method improves the performance of clustering on different public datasets and demonstrates its reasonability and superiority.

Simple PI-PD tuning rules based on the centroid of the stability region for controlling unstable and integrating processes.

Abstract: Designing the parameters of a PI-PD controller is very challenging. Consequently, the centroid of the convex stability boundary locus approach was employed to overcome this challenge. Unfortunately, this approach requires deriving several equations for constructing the stability regions of the PI-PD controller. Also, it computes the centroid of the stability region based on visual observations without using any analytical methods. Therefore, it is time-consuming, and the accuracy of its computations is questionable. This paper suggests simple tuning rules for computing the gains of PI-PD controllers based on the centroid of the stability region to handle the limitations of the centroid of the convex stability boundary locus approach. A robustness analysis has also been conducted to gauge the performance of the proposed tuning rules. Moreover, several simulation examples and a real-time application have been considered for evaluating the effectiveness and the feasibility of the suggested approach.

A Self-Guided Reference Vector Strategy for Many-Objective Optimization

Abstract: Generally, decomposition-based evolutionary algorithms in many-objective optimization (MaOEA/Ds) have widely used reference vectors (RVs) to provide search directions and maintain diversity. However, their performance is highly affected by the matching degree on the shapes of the RVs and the Pareto front (PF). To address this problem, this article proposes a self-guided RV (SRV) strategy for MaOEA/Ds, aiming to extract RVs from the population using a modified k -means clustering method. To give a promising clustering result, an angle-based density measurement strategy is used to initialize the centroids, which are then adjusted to obtain the final clusters, aiming to properly reflect the population's distribution. Afterward, these centroids are extracted to obtain adaptive RVs for self-guiding the search process. To verify the effectiveness of this SRV strategy, it is embedded into three well-known MaOEA/Ds that originally use the fixed RVs. Moreover, a new strategy of embedding SRV into MaOEA/Ds is discussed when the RVs are adjusted at each generation. The simulation results validate the superiority of our SRV strategy, when tackling numerous many-objective optimization problems with regular and irregular PFs.

Robust Federated Learning With Noisy Labels

Abstract: Federated learning enables local devices to jointly train the server model while keeping the data decentralized and private. In federated learning, all local data should be annotated by alternative labeling techniques since the annotator in the server cannot access the data. Therefore, it is hardly guaranteed that they are correctly annotated. Under this noisy label setting, local models form inconsistent class decision boundaries with one another, and their weights severely diverge, which are serious problems in federated learning. To solve these problems, we introduce a novel federated learning scheme that allows the server to cooperate with local models by interchanging class-wise centroids. The server aligns the class-wise centroids, which are central features of local data on each device, and broadcasts aligned centroids to selected clients every communication round. Updating local models with the aligned centroids helps us to form consistent class decision boundaries among local models, although the noise distributions in clients’ data are different from each other. Furthermore, we introduce a sample selection approach to filter out data with noisy labels and a label correction method to adjust the labels of noisy instances. Our experimental results show that our approach is noticeably effective in federated learning with noisy labels.

Coal gangue image segmentation method based on edge detection theory of star algorithm

Abstract: ABSTRACT Aiming at the difficult problem of coal gangue image segmentation in complex backgrounds, this paper proposes an image segmentation method based on the edge detection theory of the star algorithm. The pixel matrix is extracted one by one in the X and Y directions of the coal gangue image, and the central pixel of the matrix satisfying the monotonic change condition is assigned as 0. They are mapped to single-value images with equal size in turn, to realize the detection of coal and gangue edges in the images. The response strategy of adjusting matrix length n and assignment factor β in real-time by using the feedback result of the illuminance meter in changing illumination environment is given. Combining the edge detection method of the star algorithm with the morphological method, the fine segmentation of the coal gangue image is completed. The segmentation results are based on the segmentation results obtained by the AI algorithm, and the error rates of the pixel area and centroid coordinates of coal gangue are within 0.29%. This study provides a novel, precise and efficient solution to the problem of image edge detection and segmentation in complex backgrounds. HIGHLIGHTS A new method of coal gangue edge detection. Adapt to the complex background and illumination change conditions. The area and position information of coal gangue can be extracted quickly and accurately. It provides a new scheme to solve the background segmentation problem in coal gangue recognition.

Deep metric learning for accurate protein secondary structure prediction

Abstract: Predicting the secondary structure of a protein from its amino acid sequence alone is a challenging prediction task for each residue in bioinformatics. Recent work has mainly used deep models based on the profile feature derived from multiple sequence alignments to make predictions. However, the existing state-of-the-art predictors usually have higher computational costs due to their large model sizes and complex network architectures. Here, we propose a simple yet effective deep centroid model for sequence-to-sequence secondary structure prediction based on deep metric learning. The proposed model adopts a lightweight embedding network with multibranch topology to map each residue in a protein chain into an embedding space. The goal of embedding learning is to maximize the similarity of each residue to its target centroid while minimizing its similarity to nontarget centroids. By assigning secondary structure types based on the learned centroids, we bypass the need for a time-consuming k -nearest neighbor search. Experimental results on six test sets demonstrate that our method achieves state-of-the-art performance with a simple architecture and smaller model size than existing models. Moreover, we also experimentally show that the embedding feature from the pretrained protein language model ProtT5-XL-U50 is superior to the profile feature in terms of prediction accuracy and feature generation speed. Code and datasets are available at https://github.com/fengtuan/DML_SS .

A new validity clustering index-based on finding new centroid positions using the mean of clustered data to determine the optimum number of clusters

Abstract: • A new CVI called VCIM is proposed to validate the clustering algorithm results. • VCIM is designed to determine the optimal number of clusters. • VCIM uses score function index and mean to find new cluster centroid positions. • VCIM outperforms other well-known CVIs for both artificial and real-life datasets. Clustering, an unsupervised pattern classification method, plays an important role in identifying input dataset structures. It partitions input datasets into clusters or groups where either the optimum number of clusters is known in prior or automatically determined. In the case of automatic clustering, the performance is evaluated using a cluster validity index (CVI), which determines the optimum number of clusters in the data. From previous works, the improper cluster centroids positioning produced by clustering algorithms could reduce the performance of the validation process and performance produced by the previous state-of-the-art CVIs. In addition, those previous CVIs can only work properly with certain clustering algorithms and simple datasets structures, which their performances will reduce if they are applied to other clustering algorithms as well as more complex datasets. This study proposes an efficient CVI, namely, the validity clustering index based on finding the mean of clustered data (VCIM). The proposed approach combines the properties of the score function index and the mean to determine new cluster centroid positions. The performance of the VCIM index is compared with well-known CVIs on both artificial and real-life datasets. The obtained results on artificial datasets show that the proposed VCIM index outperforms the other CVIs in determining the true number of clusters for the five conventional clustering algorithms, namely, K-means, Fuzzy C-mean, agglomerative hierarchical average linkage clustering, variance-based differential evolution, and density peaks clustering and Particle swarm optimization (PDPC) algorithms. For the 14 real-word datasets, the proposed VCIM index correctly determined the optimum number of clusters for 11 out of 14 for the K-means clustering algorithm, 9 out of 14 for both Fuzzy clustering and agglomerative hierarchical average linkage clustering algorithms, 12 out of 14 for the variance-based differential evolution algorithm and 11 out of 14 datasets for PDPC. The obtained results using the proposed VCIM show its significance when combined with clustering algorithms and nominate its potential in various clustering applications.

Automatic Radar-Camera Dataset Generation for Sensor-Fusion Applications

Abstract: Withheterogeneous sensors offering complementary advantages in perception, there has been a significant growth in sensor-fusion based research and development in object perception and tracking using classical or deep neural networks based approaches. However, supervised learning requires massive labeled data-sets, that require expensive manual labor to generate. This paper presents a novel approach that leverages YOLOv3 based highly accurate object detection from camera to automatically label point cloud data obtained from a co-calibrated radar sensor to generate labeled radar-image and radar-only data-sets to aid learning algorithms for different applications. To achieve this we first co-calibrate the vision and radar sensors and obtain a radar-to-camera transformation matrix. The collected radar returns are segregated by different targets using a density based clustering scheme and the cluster centroids are projected onto the camera image using the transformation matrix. The Hungarian Algorithm is then used to associate the radar cluster centroids with the YOLOv3 generated bounding box centroids, and are labeled with the predicted class. The proposed approach is efficient, easy to implement and aims to encourage rapid development of multi-sensor data-sets, which are extremely limited currently, compared to the optical counterparts. The calibration process, software pipeline and the data-set generation is described in detail. Furthermore preliminary results from two sample applications for object detection using the data-sets are also presented.