Search

When recognizing targets by unmanned aerial vehicles (UAVs), problems such as small size, dense dispersion, and complex background are likely to occur, resulting in low recognition rates. In order to solve the above problems, this work proposed a lightweight small target detection algorithm based on the YOLOv8n: STD-YOLOv8 algorithm. First, the regression problem of small targets in different training periods was optimized, the penalty term in the original loss was improved, and a new LIoU loss function was proposed, so that the size of the penalty term could be dynamically adjusted before and after training, thus improving the performance of the algorithm. Second, in order to better adapt to the small target scale and enhance the ability of small target feature acquisition, the SPD-Conv module was integrated in the backbone network, replacing the original stepwise convolutional layer and pooling layer, so as to solve the problems of loss of fine-grained information and low efficiency of feature representation existing in the current convolutional neural network (CNN) structure. In the neck part, nearest-neighbor upsampling was replaced by the feature reassembly assembly of features operator CARAFE (content-aware reassembly of features), which enabled the model to aggregate contextual information in a larger perceptual field and enhanced the feature representation in the neck. Finally, validation experiments were conducted by comparing different algorithms under the same VisDrone-2021 dataset. The results of the ablation experiments show that the algorithms proposed in this thesis have improved the recall (R), mAP50, and mAP95 by 4.7, 5.8 and 5.7%, respectively, compared with YOLOv8n. The results of the model generalization experiments on the TinyPerson dataset show that the algorithm in this paper has superior small target detection performance with only 1.2 M model parameters (1 M = 106). [ABSTRACT FROM AUTHOR]

Commonly, environmental processes are observed across different locations, and observations present skewed distributions. Recent proposals for analyzing data in their original scale, accommodating spatial structure and skewness, involve two independent Gaussian processes (GP). We focus on a skewed spatial process defined through a convolution of Gaussian and log Gaussian (GLGC) processes. Because of the inclusion of two GPs, the inference procedure quickly becomes challenging as the sample size increases. We aim to investigate how recently developed approximate GPs perform in modeling high-dimensional GLGC processes. Three methods are formulated based on the nearest neighbor (NN) and Hilbert space (HS) methods, and their performances are investigated in comparison with the exact inference using simulation studies. All the approximate methods yield results comparable to exact inference, but the HS-based method provides the fastest inference of moderate to very smooth processes. A hybrid approach incorporating NN and HS methods is preferred for faster inference with improved MCMC efficiency for a wiggly process.Supplementary materials accompanying this paper appear online. [ABSTRACT FROM AUTHOR]

The field of machine learning (ML) has witnessed significant advancements in recent years. However, many existing algorithms lack interpretability and struggle with high-dimensional and imbalanced data. This paper proposes SPINEX, a novel similarity-based interpretable neighbor exploration algorithm designed to address these limitations. This algorithm combines ensemble learning and feature interaction analysis to achieve accurate predictions and meaningful insights by quantifying each feature's contribution to predictions and identifying interactions between features, thereby enhancing the interpretability of the algorithm. To evaluate the performance of SPINEX, extensive experiments on 59 synthetic and real datasets were conducted for both regression and classification tasks. The results demonstrate that SPINEX achieves comparative performance and, in some scenarios, may outperform commonly adopted ML algorithms. The same findings demonstrate the effectiveness and competitiveness of SPINEX, making it a promising approach for various real-world applications. • SPINEX: An interpretable neighbor exploration algorithm is presented. • Combines ensemble learning and feature interaction for meaningful insights. • Quantifies feature contributions and interactions to enhance interpretability. • 59 experiments were conducted to validate SPINEX's comparative performance. [ABSTRACT FROM AUTHOR]

• An efficient approach for image quality assessment is proposed. • It uses perceptual features such as texture, structure, and patterns to measure image quality. • The various experimentations are carried out on LIVE-II, TID2008, TID2013, and CSIQ datasets. • The proposed approach is efficient as compared to existing methods. In this paper, a human visual system (HVS) based no-reference image quality assessment model (NR-IQA) is proposed. This is an objective NR-IQA model that uses perceptual features such as structure and orientation to compute the loss of naturalness in the image. An adaptive feature extraction process is modeled to capture the underlying significant features of the images along with the noise. Moreover, the optimal subset of features is derived using the neighborhood component analysis and further used as inputs to the Gaussian process for regression. The various experimentations are carried out on LIVE, TID2008, and TID2013 databases to test the effectiveness of the proposed approach. It is observed that the presented model exhibits a competitive performance in comparison with the existing IQA approaches. Moreover, the computation complexity and run-time show the effectuality of the proposed approach. Further, the experiments show that the predicted score matches with human perceptions. Thus, the proposed model is more accurate, less complex, independent of distortions, and well-suited for real-time applications. [ABSTRACT FROM AUTHOR]

Locally Sensitive Hashing (LSH) algorithms are classical algorithms commonly used on the c-Approximate Nearest Neighbor (c-ANN) search problem. When using Euclidean distance to measure sample similarity and solve the c-ANN problem, the traditional approach is to utilize the Exact Euclidean Locality Sensitive Hashing (E2LSH) algorithm based on the p-stable distribution. However, the uncertainty of the p-stable distribution causes the hash buckets constructed by the E2LSH algorithm to vary in queries. Therefore, this paper proposes the OLLSH algorithm based on the Weighted Majority algorithm in the Online-Learning framework, which selects the hash buckets with more stable query accuracy by weighted voting on the hash buckets generated by the E2LSH algorithm. Then, we conduct simulation experiments on synthetic dataset and four real data sets and conclude that the proposed OLLSH algorithm improves the accuracy compared to the original algorithm with the same memory usage. • The parameters of the E2LSH algorithm are analysed in detail. • The choice of hash buckets for the E2LSH algorithm is achieved with the WM algorithm. • The OLLSH algorithm saves memory by using less hash buckets during the query process. • The efficacy of the OLLSH algorithm was proved on both synthetic and real datasets. [ABSTRACT FROM AUTHOR]