Pyramid Strategy Research Articles

A Deformable and Multi-Scale Network with Self-Attentive Feature Fusion for SAR Ship Classification

The identification of ships in Synthetic Aperture Radar (SAR) imagery is critical for effective maritime surveillance. The advent of deep learning has significantly improved the accuracy of SAR ship classification and recognition. However, distinguishing features between different ship categories in SAR images remains a challenge, particularly as the number of categories increases. The key to achieving high recognition accuracy lies in effectively extracting and utilizing discriminative features. To address this, we propose DCN-MSFF-TR, a novel recognition model inspired by the Transformer encoder–decoder architecture. Our approach integrates a deformable convolutional module (DCN) within the backbone network to enhance feature extraction. Additionally, we introduce multi-scale self-attention processing from the Transformer into the feature hierarchy and fuse these representations at appropriate levels using a feature pyramid strategy. This enables each layer to leverage both its own information and synthesized features from other layers, enhancing feature representation. Extensive evaluations on the OpenSARShip-3-Complex and OpenSARShip-6-Complex datasets demonstrate the effectiveness of our method. DCN-MSFF-TR achieves average recognition accuracies of 78.1% and 66.7% on the three-class and six-class datasets, respectively, outperforming existing recognition models and showcasing its superior capability in accurately identifying ship categories in SAR images.

The Story Pyramid Strategy's Effect on Students' Narrative Writing (Experimental Study of SMP N 3 Jambi at Eighth Grade Students)

Tujuan dari penelitian ini adalah untuk mengetahui apakah ada pengaruh yang signifikan dari penggunaan Strategi Piramida Cerita Terhadap Kemampuan Menulis Teks Naratif Siswa Kelas VIII Semester Pertama di SMP N 3 Jambi Tahun Ajaran 2023/2024. Ada dua variabel dalam penelitian ini, yaitu variabel bebas adalah strategi piramida cerita (X) dan variabel terikat adalah hasil belajar menulis teks naratif (Y). Dalam penelitian ini, metodologi yang digunakan adalah desain kuasi-eksperimen dengan pre-test dan post-test. Populasi penelitian ini adalah siswa kelas sembilan di SMP N 3 Jambi pada Tahun Ajaran 2023/2024. Sampel penelitian ini adalah dua kelas yang terdiri dari 23 siswa untuk kelas eksperimen dan 22 siswa untuk kelas kontrol. Dalam mengumpulkan data, instrumen yang digunakan adalah pre-test dan post-test. Setelah memberikan post-test, peneliti menganalisis data dengan menggunakan SPSS. Dari analisis data yang dihitung dengan menggunakan SPSS, diperoleh Sig = 0,021. Hal ini berarti Ha diterima karena Sig < 0,05. Jadi, terdapat Pengaruh Strategi Piramida Cerita terhadap Keterampilan Menulis Teks Naratif Siswa Kelas VIII Semester Pertama di SMP N 3 Jambi Tahun Ajaran 2023/2024.

SIIF: Semantic information interactive fusion network for photovoltaic defect segmentation

Any defects or damage on photovoltaic panels significantly reduce photoelectric conversion efficiency and service life. Therefore, the refined defect segmentation technology is the key to the quality inspection of photovoltaic equipment. However, the existing methods ignore the information interaction between multi-levels, causing semantic features to be easily lost and difficult to fuse. In this paper, we propose a segmentation network based on an interactive fusion of semantic information for solar cell defect identification, which can effectively interact with multi-level rich information and enhance the positioning capabilities of high-level semantics. Specifically, we propose a novel Multi-Level Pyramid Strategy (MLPS) to reduce the information gap between multi-level features. MLPS adopts a pooling distribution mechanism to enable multi-level features to interact effectively in the feature pyramid. In addition, to effectively integrate high-level positioning semantics into the neighbor level, we design a new Neighbor Attention Fusion module (NAF) to propagate high-level semantic information gradually. NAF learns spatial neighbor-level similarity combined with high-level attention to balance location information and contextual features. We perform comprehensive experiments to demonstrate the advancement of our approach. Our method achieves 84.3% MIOU on our solar cell dataset, outperforming existing state-of-the-art (SOTA) methods. To verify the generalization ability of our network, we train and evaluate the PSCDE dataset. The results show that our model achieves an excellent 98.35%MIOU.

Recursive Deformable Pyramid Network for Unsupervised Medical Image Registration.

Complicated deformation problems are frequently encountered in medical image registration tasks. Although various advanced registration models have been proposed, accurate and efficient deformable registration remains challenging, especially for handling the large volumetric deformations. To this end, we propose a novel recursive deformable pyramid (RDP) network for unsupervised non-rigid registration. Our network is a pure convolutional pyramid, which fully utilizes the advantages of the pyramid structure itself, but does not rely on any high-weight attentions or transformers. In particular, our network leverages a step-by-step recursion strategy with the integration of high-level semantics to predict the deformation field from coarse to fine, while ensuring the rationality of the deformation field. Meanwhile, due to the recursive pyramid strategy, our network can effectively attain deformable registration without separate affine pre-alignment. We compare the RDP network with several existing registration methods on three public brain magnetic resonance imaging (MRI) datasets, including LPBA, Mindboggle and IXI. Experimental results demonstrate our network consistently outcompetes state of the art with respect to the metrics of Dice score, average symmetric surface distance, Hausdorff distance, and Jacobian. Even for the data without the affine pre-alignment, our network maintains satisfactory performance on compensating for the large deformation. The code is publicly available at https://github.com/ZAX130/RDP.

Contactless weighing method based on deep learning and acoustic levitation

Abstract Acoustic weighing is a promising contactless method for screening the mass of micro-nano objects as it avoids contact contamination and losses. Existing acoustic weighing methods determine the mass of an object by detecting its oscillation trajectory with a laser sensor. However, this method suffers from several limitations, such as short measurement distance, poor accuracy in measuring transparent objects, and inducing damage to photosensitive samples. To solve these issues, this work proposes a contactless weighing method based on location-aware neural network (LANet) and acoustic levitation. The proposed LANet is a deep learning-based image processing method that detects object bit oscillation trajectories completely contactless, regardless of the color, shape, and oscillation distance of the levitated object. We employ a cross-stage aggregation module and cross-mixed feature pyramid strategy to build LANet network depth for enhanced feature extraction. In addition, to create a contactless environment, we built an acoustic levitation system, which drives the oscillation of objects. Finally, we verified the accuracy and effectiveness of the method. The results show that the proposed network can accurately detect the oscillation trajectories of various objects with high detection performance, even for small objects in low-contrast backgrounds. Meanwhile, the proposed method can accurately measure the mass of objects with a percentage error of no more than 7.83%.

Improving Students’ Reading Comprehension by Using Story Pyramid and Plus Minus Interesting Strategy

This research shows that there were several problems faced by students at SMA Negeri 2 Alasa in learning English, especially learning reading comprehension. Therefore, researcher was interested in conducting research entitled " Improving Students’ Reading Comprehension by Using Story Pyramid and Plus Minus Interesting Strategy at the Tenth Grade of SMA Negeri 2 Alasa". This research aims to observe the learning difficulties of these students, whether using the Story Pyramid and Plus Minus Interesting strategies could improve reading comprehension skills of the tenth grade students at SMA Negeri 2 Alasa and find out which strategy was more effective in improving reading comprehension skills. In this research, the researcher used classroom action research (CAR). CAR is an examination of learning activities in the form of an action, which is carried out to improve the teaching and learning process so as to improve learning outcomes that are better than before. Based on the results of the analysis, the pre-test results in class X-IPS which used the Story Pyramid strategy obtained an average score of 61.05%, while in class X-IPA got 56,84%. After the students learned by using these two strategies, the average post-test score for class X-IPS was 73.68% and class X-IPA was 74.21%. From these calculations it was concluded that there was a significant improvement in students' scores in reading comprehension and the use of Plus Minus Interesting strategy was more effective in improving students' reading comprehension with an average score increase of 17.37% compared to Story Pyramid's 12.63%.

A Simulation Study of Aircraft Boarding Strategies

To ensure the safety of passengers concerning virus propagation, such as COVID-19, and keep the turnaround time at low levels, airlines should seek efficient aircraft boarding strategies in terms of both physical distancing and boarding times. This study seeks to analyze the impact of different boarding strategies in the context of the International Air Transport Association’s recommendations during the pandemic to reduce interference and physical contact between passengers in airplanes. Boarding strategies such as back-to-front, outside-in, reverse pyramid, blocks, Steffen, and modified optimal have been tested in this context. This study extends the previous literature using discrete event simulation to evaluate the impact of the occupation of the middle seat by family members only. This study also analyses the impact of having passengers carrying hand luggage and priority passengers on the performance of these strategies concerning boarding times. In general, the simulation results revealed a 15% improvement in boarding times when the reverse pyramid strategy is used compared to a random strategy, which essentially results from a reduction in the boarding interferences between passengers. The results also show that Steffen’s strategy is the best performing, while the blocks strategy results in the worst performance. This study has practical implications for airline companies concerning both operation efficiency and passenger safety.

Multiscale self-calibrated pulmonary nodule detection network fusing dual attention mechanism

Objective. In this study, we propose a model called DEPMSCNet (a multiscale self-calibration network) that has a high sensitivity and low false positive rate for detecting pulmonary nodules. Approach. First, at the feature extraction stage, we propose to use the REPSA-MSC module instead of the traditional convolutional neural network. The module extracts multiscale information from the feature map based on the image pyramid strategy while introducing adaptive convolutional branches to detect contextual information at each position of the multiscale, thereby expanding the receptive field and improving sensitivity. At the same time, multiple branches are adaptively weighted by channel attention, and the weights of different branches are adjusted to better generate pixel-level attention. Secondly, the proposed DSAM (dual-path spatial attention module) operates at the information fusion stage. This module fully exploits the rich spatial information of CT scans, obtains receptive field information from two branches, combines low-level feature map information with high-level semantic information, and enhances location-related information to effectively improve specificity. Thirdly, the focal loss function is used to solve the problem of positive and negative sample imbalance. Main results. The proposed model has been evaluated on the public lung nodule analysis (LUNA16) challenge dataset. The technique outperforms the most recent state-of-the-art detection algorithms in terms of sensitivity and specificity, obtaining a sensitivity of 0.988 and a competitive performance metric (CPM) of 0.963. Significance. Ablation experiments show that the two modules proposed in this paper effectively reduce false positives and improve sensitivity. This model effectively reduces the number of false positive nodules that doctors see on CT scans.

A Fast Large-Scale Path Planning Method on Lunar DEM Using Distributed Tile Pyramid Strategy

In lunar exploration missions, path planning for lunar rovers using digital elevation models (DEMs) is currently a hot topic in academic research. However, research on path planning using large-scale DEMs has rarely been discussed, owing to the low time efficiency of existing algorithms. Therefore, in this article, we propose a fast path-planning method using a distributed tile pyramid strategy and an improved A <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">*</sup> algorithm. The proposed method consists of three main steps. First, the tile pyramid is generated for the large lunar DEM and stored in Hadoop distributed file system. Second, a distributed path-planning strategy based on tile pyramid (DPPS-TP) is used to accelerate path-planning tasks on large-scale lunar DEMs using Spark and Hadoop. Finally, an improved A <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">*</sup> algorithm was proposed to improve the speed of the path-planning task in each tile. The method was tested using lunar DEM images. Experimental results demonstrate that: in a single-machine serial strategy using source DEM generated by the Chang'e-2 CCD stereo camera, the proposed A <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">*</sup> algorithm for open list and closed list with random access feature (OC-RA-A <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">*</sup> algorithm) is 3.59 times faster than the traditional A <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">*</sup> algorithm in long-distance path planning tasks and compared to the distributed parallel computation strategy using source DEM generated by the Chang'e-2 CCD stereo camera, the proposed DPPS-TP based on tile pyramid DEM is 113.66 times faster in the long-range path planning task.

Digital educational environment: Effectiveness of adaptive testing of medical students

BACKGROUND: The computer-adaptive approach in testing is becoming more widespread, and research and optimization of algorithms for its work are underway, especially in the pedagogical sphere. According to literature data, adaptive testing has several advantages over traditional linear testing of knowledge, which determined the purpose and objectives of the study.&#x0D; AIM: To assess the feasibility of using an adaptive approach in digital test control of the knowledge of students majoring in Dentistry, through a comparative analysis of their psycho-emotional state, success of the test task completion, and time spent.&#x0D; MATERIAL AND METHODS: In this study, we considered the simplest mechanism of the algorithm (pyramid strategy) to ensure the adaptive operation of a computer test. The study included 446 first-year students of the Moscow State Medical University named after A.I. Evdokimov, who were majoring in dentistry (average age 18.762.26 years), divided into two groups: control group (n=200), in which linear testing was conducted, and experimental group (n=246), in which adaptive testing was conducted. The testing process is implemented through publicly available electronic resources and platforms.&#x0D; RESULTS: As the result of the study the absence of statistically significant differences in all parameters (p 0.05), except for time costs (p 0.05), was determined.&#x0D; CONCLUSIONS: The results of the study emphasized the feasibility of an adaptive approach in digital test control of the knowledge of students majoring in Dentistry.

Effect of the preferences pyramid strategy on providing second-grade students with deep understanding skills

The research aims to find out the effect of the priority pyramid strategy on providing second-grade intermediate students with deep understanding skills. In order to verify the objective of the research, the researcher developed a null hypothesis regarding the variables of her research. The effectiveness of the priority pyramid strategy in providing second-grade intermediate students with deep understanding skills compared to the usual method. The possibility of applying the priority pyramid strategy in teaching biology to second-grade intermediate students. Adoption of the pyramid of preference strategy in teaching that makes female students more interesting and interesting for the lesson and interacting with the study material, as it has created an enjoyable cooperative and interactive study environment.

M3SPCANet: A simple and effective ConvNets with unsupervised predefined filters for face recognition

The principal component analysis network (PCANet) with predefined filters has recognized as a lightweight convolutional neural networks (CNN) baseline. However, there are three shortages in PCANet: (i) single-scale convolution leads to insufficient feature learning, (ii) the spatial layout information and relationship between channel features are neglected, (iii) lack of nonlinearity because there is no activation function. Therefore, we devise a PCANet alternative dubbed Multi-Scale Spatial pyramid Second-order pooling Principle Component Analysis Network (M3SPCANet) in the paper. First, multi-scale PCA filters are learned and applied to obtain feature maps via convolution. Second, the feature maps are activated via nonlinear function Tanh and stacked together. Third, second-order pooling is exploited to extract correlation information between any two channels of the feature maps, moreover, spatial pyramid strategy is employed to learn local and holistic features simultaneously. Finally, whitening PCA based fully connected layer is constructed to remove redundancy information. We utilize cosine similarity based nearest neighbor classifier for face matching. Extensive experiments on four homogeneous and one heterogeneous face databases indicate that our method can achieve superior identification rates, and yield competitive verification performance. Cross database evaluations demonstrate that the multi-scale filters of our method have strong generalization ability. Our implementation code will be available at https://github.com/dxtyut/facerecognition.

Using Story Pyramid Strategy for Developing Reading Comprehension Skills and Reducing Reading Anxiety among Preparatory Stage EFL Pupils

Using Story Pyramid Strategy for Developing Reading Comprehension Skills and Reducing Reading Anxiety among Preparatory Stage EFL Pupils

Directionally separable dilated CNN with hierarchical attention feature fusion for hyperspectral image classification

ABSTRACT In recent years, the convolutional neural network (CNN) plays a vital role in hyperspectral image classification and performs more competitively than many other methods. However, in order to pursue better performance, most of existing CNN-based methods just simply stack rather deep convolutional layers. Although they improve the classification accuracy to a certain extent, they result in plenty of network parameters. In this paper, a light-weighted directionally separable dilated CNN with hierarchical attention feature fusion (DSD-HAFF) is proposed to solve these problems. First, two global dense dilated CNN branches that focus on two spatial directions separately are constructed to extract and reuse spatial information as much as possible. Second, a hierarchical attention feature fusion branch that consists of several coordinate attention blocks (CABs) is constructed. Hierarchical features from two directionally separable dilated CNN branches are adopted as inputs of CABs. In this way, the structure can not only fully incorporate hierarchical features, but also significantly reduce the network parameters. Meanwhile, the hierarchical attention feature fusion branch incorporates features from high-level to low-level in the kernel-number pyramid strategy. Experimental results on three popular benchmark datasets demonstrate that the DSD-HAFF achieves better performance and has a much smaller number of network parameters than the other state-of-the-art methods.

Multi-Exposure Image Fusion based on Window Segmentation and a Laplacian Pyramid for Chip Package Appearance Quality Detection

A heterogeneous material image enhancement method based on multi-exposure image fusion is proposed to address the problem of obtaining high-quality images from the single imaging of chips containing two extremely different reflectivity materials. First, a multi-exposure image fusion algorithm based on window segmentation and Laplacian pyramid fusion is proposed. Then, orthogonal experiments are used to optimize the parameters of the imaging system. Next, a method based on information entropy and average gray intensity is utilized to calculate the imaging exposure times of two heterogeneous materials, and two exposure time ranges are obtained that are appropriate for regions with high and low reflectivity. Finally, the subjective and objective experimental evaluations are conducted after the multi-exposure image set has been established. The results show that the fused image has a good visual effect, the information entropy is 6.29, and the average gray intensity is 131.56. In addition, time consumption is reduced by an average of 20.3% compared to the Laplace pyramid strategy. The heterogeneous material enhancement method based on multi-exposure image fusion proposed in this paper is effective and deserving of further research and application.

AVS-YOLO: Object Detection in Aerial Visual Scene

Difficult object detection and class imbalance in object detection are the two main challenges faced by aerial image object detection. Difficult objects include small objects, objects of scale variation and objects with serious background interference. Class imbalances come from the number of different classes of objects and sampling of positive and negative samples. Due to these challenges, conventional object detection models usually cannot effectively detect objects in aerial images, especially in the balance between network speed and accuracy. In this paper, the YOLOv3 network structure was improved and an object detection method under the aerial visual scene (AVS-YOLO) was proposed. By introducing a type of densely connected feature pyramid strategy, a scale-aware attention module was constructed, considering both residual dense network blocks and the median-frequency-balancing mechanism. On this basis, an algorithm with ideal speed and accuracy for object detection is obtained. To verify the effectiveness of the algorithm, AVS-YOLO and YOLOv3 were both used to test the VisDrone-DET2019 and UAVDT. The experimental results show that the AP of AVS-YOLO increases by 6.22% and 5.09% on the VisDrone2019 and UAVDT datasets, respectively, compared with YOLOv3. In addition, the AP of AVS-YOLO is 1.82% higher than that of YOLOv4 on the VisDrone2019 dataset. In terms of detection speed, AVS-YOLO can process 31.8 frames per second on a single Nvidia GTX 2080Ti GPU, compared with 44.1 frames per second for YOLOv3. Compared with the other one-stage network in the field of object detection, AVS-YOLO currently achieves the state-of-the-art performance with similar calculation amount on this dataset.

Studying Formability Limits By Combining Conventional and Incremental Sheet Forming Process

In this work it is assessed the potential of combining conventional and incremental sheet forming processes in a same sheet of metal. This so-called hybrid forming approach is performed through the manufacture of a pre-forming by conventional forming, followed by incremental sheet forming. The main objective is analyzing strain evolution. The pre-forming induced in the conventional forming stage will determine the strain paths, directly influencing the strains produced by the incremental process. To conduct the study, in the conventional processes, strains were imposed in three different ways with distinct true strains. At the incremental stage, the pyramid strategy was adopted with different wall slopes. From the experiments, the true strains and the final geometries were analyzed. Numerical simulation was also employed for the sake of comparison and correlation with the measured data. It could be observed that single-stretch pre-strain was directly proportional to the maximum incremental strains achieved, whereas samples subjected to biaxial pre-strain influenced the formability according to the degree of pre-strain applied. Pre-strain driven by the prior deep-drawing operation did not result, in this particular geometry, in increased formability.

WITHDRAWN: The impact of story pyramid strategy on university students' reading comprehension performance level

The present study aims at finding out the effect of story pyramid strategy on the performance of EFL university students in reading comprehension. The design of the present study is the Quasi experimental with a non –randomized control group, pretest–posttest with experimental and control groups. The sample of the study includes (40) male college students. All of them have been selected from the 3rd stage university students / College of Physical Education and Sport Sciences. Face validity and reliability coefficient of the pretest and posttest have been computed. Mann-Whitney test has been used. Results show that there is statistically significant difference between the two groups in favor of the experimental group. This means that the experimental group students have shown to be better in their reading comprehension because they have been educated by the Story Pyramid Strategy. Finally, conclusions and recommendations have been put forward.

Performance evaluation of various strategies to improve sub-ambient radiative sky cooling

Since the breakthrough of daytime radiative sky cooling, more and more effort has been devoted to this promising technology. But the low cooling performance places great restrictions on the application of this technology. In this work, various strategies are used to further improve the radiative cooling performance. The theoretical analysis reveals that the parameters corresponding to different strategies have great impact on the cooling performance. The experiments with individual strategy indicate that nano polyethylene wind cover strategy can achieve daytime temperature drop of about 5.6 K, improving by about 143.4% compared to that without wind cover (2.3 K). And ordinary polyethylene wind cover strategy and tilt strategy can also achieve daytime temperature drop of about 3.2 K and 4.3 K, improving by about 78.3% and 39.1%, respectively. But inverted pyramid strategy reduces daytime cooling performance by about 33%, due to the higher solar intensity on the radiative cooler. Subsequently, experiments with combined strategy show that the combination of nano polyethylene wind cover strategy and tilt strategy can enable radiative cooler achieve the higher all-day cooling performance, comparable to the results in arid areas. Further discussion on other strategies indicates that polyethylene aerogel has great potential in further improving the cooling performance.

‘STORY PYRAMID’: AN INOVATION OF ENGLISH TEACHING STRATEGY IN PROMOTING STUDENTS’ READING SKILL

Some problems are faced by students in reading of English text. The interesting strategy is needed to teach them. Story Pyramid Strategyis one of strategies to teach reading comprehension. This strategy forces students to review and summarize the main points of a story. The research aimed at knowing the effectiveness of using story pyramid strategy in teaching narrative text toward students’ reading comprehension was conducted in SMAN 1 Serang. The research design of this reseacrh was quasi experimental research with quantitative approach. The research finding showed that Story Pyramid Strategy is effective in teaching narrative text toward students’ reading comprehension to Senior High School.