Search

Fine-grained remote sensing ship detection is crucial in a variety of fields, such as ship safety, marine environmental protection, and maritime traffic management. Despite recent progress, current research suffers from the following three major challenges: insufficient features representation, conflicts in shared features, and inappropriate anchor labeling strategy, which significantly impede accurate fine-grained ship detection. To address these issues, we propose FineShipNet as a solution. Specifically, we first propose a novel blend synchronization module, which aims to facilitate the coutilization of semantic information from top-level and bottom-level features and minimize information redundancy. Subsequently, the blend feature maps are fed into a novel polarized feature focusing module, which decouples the features used in classification and regression to create task-specific discriminating features maps. Meanwhile, we adopt the adaptive harmony anchor labeling and propose a novel metric, harmony score, to choose high-quality anchors that can effectively capture the discriminating features of the target. Extensive experiments on four fine-grained remote sensing ship datasets (HRSC2016, DOSR, FGSD2021, and ShipRSImageNet) demonstrate that our FineShipNet outperforms current state-of-the-art object detection methods, achieving superior performance with mean average precision scores of 81.3%, 68.5%, 85.7%, and 63.9%, respectively.

Recently, significant advancements have been achieved in optimizing algorithms for synthetic aperture radar (SAR) ship detection. Nevertheless, two challenges still impede further research as follows. 1) Mainstream methods, whether anchor-free or anchor-based, adhere to a dense paradigm, leading to substantial redundancy and limited adaptability. 2) Ship targets in SAR images exhibit large shape variations and scale differences, making it difficult to efficiently extract key features from background clutter. To tackle the aforementioned problems, we propose DETR with Concentrated dEformable Attention (DCEA), a query-based method for end-to-end optimization of the current pipeline. First, for the irregular shapes and sparse distribution of ships, the concentrated deformable attention is introduced to model the spatial positions of targets, simulating their geometric transformations with precision. Second, an attentionwise propagation module is designed to integrate local fine-grained information with global semantic information, improving the detection performance for objects across diverse scales. Finally, due to the lack of information exchange between object queries, a dimensionwise information mixing module is employed to incorporate key information from various dimensions to enhance their representation capability. To validate the superior performance of DCEA, we conduct extensive experiments on multiple public datasets, achieving mean average precision scores of 0.991, 0.929, and 0.962 on the SSDD, HRSID, and SAR-Ship-Dataset, respectively, with a model size of only 14.34M parameters and 44.4 giga floating point operations.

Synthetic Aperture Radar (SAR) finds widespread applications in environmental monitoring, disaster management, ship surveillance, and military intelligence. However, existing target detection methods are ineffective in SAR scenes due to the intricate background environments, small target displays, and irregular appearances. To address these challenges, this thesis introduces a target detection model named YOLOv8-FDF, tailored for SAR scenes based on the YOLOv8 architecture. The model effectively incorporates the FADC module to distinguish targets from complex backgrounds and integrates a deformable feature adaptive mechanism to focus on irregular targets. Additionally, this thesis devised a specialized detection head designed to identify small targets in SAR-wide scenes, thereby improving the effectiveness of detecting such targets. The proposed YOLOv8-FDF model is evaluated on the HRSID dataset. Experiment results show a 3.6% improvement in Map75 on both the training and test sets. Furthermore, under the COCO standard, the model achieves improvements of 4.1%, 2.9%, and 5.5% on AP, AP50, and AP75, along with 6.8%, 1.2%, and 1.2% improvements on small, medium, and large-sized ship detection. An accuracy enhancement of 6.8%, 1.0%, and 14.9% is achieved. These experimental findings validate the efficacy of the proposed YOLOv8-FDF model in SAR scenarios.

Traditional pattern mining algorithms are based on tree and linked list structures. However, they often only consider a single factor of frequency or utility and have to deal with exponential search spaces as well as generate numerous candidates. Thus, we propose a frequent closed high-utility itemset mining (FCHUIM) algorithm based on Leiden community detection and a compact genetic algorithm (LcGA). This algorithm first employs Leiden community detection to decompose a dataset into several highly related transaction communities and then uses an approximate or exact strategy to mine frequent itemsets. Subsequently, it checks for closures in the mined frequent itemsets and finally employs the compact genetic algorithm to efficiently mine high-utility patterns from the frequent closed itemsets. Experimental results on four real datasets, namely Retail, Chainstore, Chess, Accidents,among which the datatype of the former two is Sparse and that of the latter two is Dense, demonstrate that compared with modified traditional closed high-utility mining algorithms, including CHUI-Miner-S, CLS-Miner-S and the most advanced algorithms for mining frequent closed high-utility mining algorithms called FCHUIM, the average runtime of LcGA-FCHUIM is lower by 40.5% than the optimal contrastive algorithm. Moreover, LcGA-FCHUIM can mine an average of 96% of frequent closed high-utility itemsets, making it an effective algorithm for frequent closed high-utility itemset mining and suitable for most scenarios.

The high-frequency trading framework for the price trend prediction model and trading strategy has been a popular approach for T+0 trading in the stock market. The prediction model is used to predict price trends, and the trading strategy is used to determine the price and volume of the order. Most trading strategies consist of multiple trading logic associated with certain tuning parameters. These parameters significantly affect the profitability of high-frequency trading frameworks. There are two main disadvantages of this framework: 1) the price trend prediction model can not adapt to the current market data distribution, and 2) the trading strategy can not adapt to the current market conditions automatically. Thus, the framework cannot always maintain positive revenue. To address this problem, we propose a novel dynamic parameter optimization algorithm based on reinforcement learning for stock prediction and trading, and to generate an adaptive trading framework. First, we use a rolling model training method for stock price trend prediction. Second, we regard each set of strategy parameters as action and devise an inverse reinforcement learning algorithm for the reward function to accurately estimate the reward of each action. Because of the T+1 trading rules of the Chinese stock market, we consider the constraint of limited short position in the reward function. Finally, a reward-enhanced upper confidence bound (UCB) selection algorithm is proposed to automatically optimize the parameters of the trading logic in real-time trading. The experimental results show that our method achieves competitive performance in the Chinese stock market.

Price prediction using machine learning is a heated topic and an effective task in quantitative trading. However, the objectives that existing researches focus on are typically naive and can hardly express the diverse properties in real trading, by using which the results of price prediction cannot precisely reflect the returns in real trading. To alleviate this problem, we first formulate the characteristics of transactions and then propose a multi-objective method under a real-trading-oriented perspective, where a tree model inducing explainable trading characteristics is proposed. With lots of considerations of real trading characteristics, the results of price prediction can better obtain the properties in trading, and especially perform quite well in real trading. Multiple experiments on the Chinese Index Future Market display the effectiveness of the proposed model, where the performance of real trading has reached the industry-leading level. In particular, the difference between model prediction and returns in real trading can be diminished.

An innovative approach, mainly featured by progressive iteration of partitioning and focusing, to processing very-high-resolution spaceborne synthetic aperture radar (SAR) data is presented in this article. Due to the long integration time endured during data acquisition as well as large scene extensions being common to the advanced SAR systems, spatial dependence of range histories may be severe and must be properly dealt with. In this article, after deriving the exact two dimensional spectrum for an curved satellite orbit, we focus the entire echo data through several iterations of partitioning and focusing. By partitioning, each partitioned data block can be better focused by the following focusing step, and meanwhile, focusing with better quality enables the following partitioning with both higher granularity and less overlapped data region. Besides, a new technique aiming at eliminating spatial dependence inside a data block is also presented and deployed in the processing procedure. Owing to the feature of high granularity partitioning, the spatial dependence of many factors can be accommodated finer and easier compared with other conventional algorithms. What is more, the artifacts caused by subaperture recombination are fundamentally avoided by the fact that the partitioned blocks are not recombined until being processed into fully focused image blocks. Finally, the precision and the efficiency of the proposed methodology are validated by results on a simulated and a real SAR data.

This paper aims to propose a comprehensive equilibrium service capability recovery model to effectively recover the service capability of a port-hinterland service network with delay or disruption risk under limited resources. We first analyze the risk factors and generation mechanism of a port-hinterland network and then introduce a differential evolution algorithm and project pursuit method to determine the risk resistance level of service nodes and regions in a port-hinterland service network for resource allocation and service capability recovery based on the selected indicators. An equilibrium utility model is used to control the equilibrium of the service capability recovery within nodes and regions in the port-hinterland service network, and the multinomial logit model is used to calculate the service path choice probability. Finally, we build this model, taking the port-hinterland service network of three provinces in Northeast China as examples to validate the model, which is solved with an elite genetic algorithm, and then perform comparisons of four scenarios. The results show that (1) external factors more easily induce delay or disruption risk than do internal factors; (2) the strategy considering equilibrium recovery is better than that without considering equilibrium recovery; (3) the strategy considering both equilibrium among the regions and inside the regions is better than that considering only region equilibrium or internal equilibrium; and (4) the strategy considering region equilibrium is better than that considering internal equilibrium.

A novel rotating machine fault diagnosis method based on multi-scale transfer fuzzy entropy (MTFE) and support vector machine (SVM) is proposed in this paper. Compared with traditional machine learning methods, our proposed method can identify various fault types of rotating machinery with different data distribution by learning the transfer knowledge from different distribution source domains. First, multi-scale fuzzy entropy (MFE) features of all samples are extracted as input. Second, build a transfer learning model to find a projection matrix to map the MFE features of the source and target domains into a common subspace, called MTFE features. In this process, the distribution structure of training data is maintained and the distribution difference between training data and test data is reduced. Finally, the SVM classifier identifies the fault type of the test data. Two cases including gearbox and rolling bearing are used for validation. Experimental results demonstrate that our proposed MTFE method performs best in recognizing various fault types comparing with other six methods.

Sea surface current is a research hotspot in oceanography. Space-borne along-track interferometric synthetic aperture radar (along-track InSAR, ATI) is a promising sensor for measuring high-resolution sea surface current field, and there is no operational system in orbit yet. To support future space-borne ATI systems, based on the ATI experimental mode of the Gaofen-3 (GF-3) satellite, the first sea surface current observing experiment was conducted in the Jiaozhou Gulf in China, in 2019. Meanwhile, SAR observations and in situ instrument measurements of the current are obtained in the experiments. The data is first preprocessed by a processor specially developed for the GF-3 ATI data. Then, the current is extracted based on the M4S mode. The retrieved current of the Jiaozhou Gulf is compared with ground-based high frequency surface wave radar data. The results show that the root mean square error of the surface current observed by the GF-3 satellite is less than 0.2 m/s.

Recent trends in consumer electronics have led to a proliferation of high dynamic range (HDR) video acquisition and transmission studies. High-end video capturing systems increase the bit depth of each pixel to adapt to the high-contrast ambient light. However, the extended bit depth is pathetically meager compared with the far wider dynamic range of the incident light. What’s more, incompatibility issues for the subsequent compression and transmission system may be arisen along with the increased bit depth. In this paper, we propose an auto complementary exposure (ACE) algorithm for optimal exposure parameter estimation under Siamese Trigger (ST) mode to maximize the entropy of the output HDR image. With the proposed algorithm, neither the sensor nor other related hardware needs to be modified. Only the auto-exposure algorithm in the firmware needs to be updated. In the proposed ACE algorithm, every two consecutive images are treated as Siamese twins, and the exposure parameters for the twin images are calculated simultaneously. The target of the ACE algorithm is not to maximize the entropy of each image but to maximize that of the fused image. Compared to existing auto exposure or bracketed fusing algorithms, the proposed algorithm has three significant advantages. Firstly, no extra bit-depth is needed to embrace the details of the scene. Thus the image transmission system is not affected. Secondly, only two raw images are necessary for one output fused HDR image. The computation load is relatively low. Thirdly, the proposed method can fit video recording, which has a broader application prospect than HDR image capturing. Experiment results on a self-built database and publicly accessible database demonstrate that the algorithm works well under various types of scenarios. Furthermore, the experiment results on the real-time system show that the captured video image reveals many details under high dynamic scenes.

Azimuth multichannel (AMC) synthetic aperture radar (SAR) is an advanced technology that can prevent the minimum antenna area constraint and provide high-resolution and wide-swath SAR images. The calibration of phase imbalance is an important topic in the AMC SAR signal processing since it has a significant impact on the image quality. For one SAR image, the phase imbalance is usually considered as a constant. However, because of the attitude errors, antenna position errors, target elevation, target motion, and phase mismatch of the antenna pattern, the actual phase imbalance is time-varying in azimuth and space-varying in range. Although the space-time variation of phase imbalances is too tiny to make a little effect on the product quality, it is still meaning to study the variation. On the one hand, it is possible to quickly estimate the phase imbalance of the whole observing operation and eliminate the influences of target motion, on the phase imbalance. On the other hand, some parameters, such as motion, can be retrieved by the phase imbalance. This article first establishes the signal models between phase imbalances and attitude errors, antennal position errors, and target elevation. Then, the signal model is verified by some simulations based on the parameters of Gaofen-3 (GF-3). In addition, the phase imbalance of the real data acquired by GF-3 is processed. Finally, based on the procession results of GF-3 real data, this article makes some discussions and points out the direction for the future work.

In this article, we propose an automatic and efficient method to solve optical and synthetic aperture radar (SAR) image registration using the improved phase congruency (PC) model. First, evenly distributed keypoints are extracted from the optical images via the block-Harris method. Complementary grid points are then selected in image regions with poor structural information and supplemented to the keypoint set. For each keypoint, a robust feature representation that captures the local spatial relationship is proposed based on the improved PC model. Specifically, we propose to use two different PC models, the classic PC and the SAR-PC, to construct features for optical and SAR images, respectively. The PC features of several directions are aggregated to construct the feature descriptors, and a similarity metric via the phase correlation of feature descriptors is obtained. The proposed similarity metric cannot only find accurate correspondence but also present efficient results without presetting the size of the search region. We compare the proposed method with two baselines and state-of-the-art (SOTA) methods, i.e., OS-SIFT, histogram of oriented PC, and channel features of oriented gradients, in various scenarios. The results show that the proposed method outperforms the baselines and shows comparable performance with SOTA methods in regions with abundant structural information and better performance in regions with less structural information. Moreover, we build a high-resolution optical and SAR image matching dataset, which consists of 10 692 nonoverlapping patch pairs of 256 × 256 pixels and 1-m resolution. Results of two benchmarks, Siamese deep matching network, and conditional generative adversarial networks show that this dataset is practical and challenging.

The Geosynchronous Synthetic Aperture Radar (GEO SAR) has a long synthetic aperture time. The temporal decoherence and azimuth variance characteristics of echo are significant, that brings great challenges to signal to process. In order to reduce the synthetic aperture time and thus improve the observation flexibility and efficiency, this paper proposes a SAR system mounted on a special satellite in reverse equatorial geosynchronous orbit, so-called the reverse equatorial GEO SAR. The orbit is nearly circular and the orbital plane coincides with the equatorial plane. The satellite flies against the direction of the Earth's rotation. The relative velocity is accelerated twice and the synthetic aperture time is shorter. The satellite does not drift in latitude direction and drifts uniformly in longitude direction. The echo has azimuth invariance property. Meanwhile, the 24-hour continuous observation can be achieved for areas with a certain range of latitude by means of large squint technique and constellation design. As the GEO SAR has high orbit, large delay, large squint angle, and wide pulse width, the complex modulation effects are generated by continuous motion between the satellite and target during the imaging period. In this paper, the uniform acceleration curve motion is used to describe the motion of both satellite and target, and the linear approximation is used to describe the slant range change in the process of transmitting and receiving one pulse. Accordingly, an accurate signal model for the reverse equatorial GEO SAR is established, which provides a theoretical model for signal characteristics analysis and imaging algorithms development.

Neoadjuvant chemotherapy (NAC) has become the main treatment option for breast cancer. Its adverse drug reactions (ADRs) make NAC painful both physiologically and psychologically. The factor pathological complete remission (pCR) describes how well a series of six or more chemotherapeutic treatments works on a patient. This study investigated the possibility of predicting pCR using only the nodal sizes of the first three treatments. A best feature combination for each breast cancer subtype was screened from the real nodal sizes of the first three treatments and the nodal sizes` of the next three treatments predicted from those of the first three ones. The prediction was evaluated by the metrics Avc = (sensitivity + specificity)/2. A triple-negative breast cancer (TN) patient may have an estimation of pCR Avc = 0.8696 after taking just three treatments. At least Avc = 0.7594 was achieved for all the four breast cancer subtypes investigated in this study.

In this paper, we propose and experimentally demonstrate a novel scheme to tailor the spectrum of random fiber laser (RFL) based on the multimode interference effect. A fiber loop mirror (FLM) incorporating multimode interference filter (MMIF) with single mode fiber (SMF)-MMF-SMF structure acts as a wavelength-dependent point reflector in half-opened RFL. By varying the length of MMF, either single wavelength random lasing with specific wavelength or multiwavelength random lasing with selective wavelength spacing can be generated in MMIF-FLM-based RFL. Due to the wide wavelength range of the MMIF, cascaded multiwavelength random lasing can also be realized. The spectrum adjustable all fiberized RFL based on the MMIF shows distinct advantages, such as easy fabrication, wide operating wavelength range, and low-cost. Besides, the MMIF-FLM can has good power handling ability, by combining the MMIF-FLM and the short-length cavity, the proposed MMIF-based forward-pumping RFL also has a great potential to generate high power, high efficiency random lasing with the adjustable spectral property.

A 1 × 8 optical splitter on silicon-on-insulator technology is demonstrated with less than ±1.0 dB imbalance for a wavelength range of 300 nm, in which, a multimode interference (MMI) structure is introduced into an optical power splitter. A comparison is provided for 1 × 2 MMI splitters with and without tapers, a 1 × 2 MMI splitter with tapers is designed, fabricated and measured, which show a wider wavelength range of 300 nm with a lower imbalance of less than ±0.25 dB and a propagation loss of 3 dB.