Direct Information Research Articles

OptiShipNet: Efficient Ship Detection in Complex Marine Environments Using Optical Remote Sensing Images

Ship detection faces significant challenges such as dense arrangements, varying dimensions, and interference from the sea surface background. Existing ship detection methods often fail to accurately identify ships in these complex marine environments. This paper presents OptiShipNet, an efficient network for detecting ships in complex marine environments using optical remote sensing images. First, to effectively capture ship features from complex environments, we designed a DFC-ConvNeXt module as the network’s backbone, where decoupled fully connected (DFC) attention captures long-distance information in both vertical and horizontal directions, thereby enhancing its expressive capabilities. Moreover, a simple, parameter-free attention module (SimAM) is integrated into the network’s neck to enhance focus on ships within challenging backgrounds. To achieve precise ship localization, we employ WIoU loss, enhancing the ship positioning accuracy in complex environments. Acknowledging the lack of suitable datasets for intricate backgrounds, we construct the HRSC-CB dataset, featuring high-resolution optical remote sensing images. This dataset contains 3786 images, each measuring 1000 × 600 pixels. Experiments demonstrate that the proposed model accurately detects ships under complex scenes, achieving an average precision (AP) of 94.1%, a 3.2% improvement over YOLOv5. Furthermore, the model’s frame per second (FPS) rate reaches 80.35, compared to 67.84 for YOLOv5, thus verifying the approach’s effectiveness.

Marine remote target signal extraction based on 128 line-array single photon LiDAR

LiDAR technology has garnered significant attention in recent years due to its superior directivity, high resolution, and precise 3D information acquisition capabilities, making it indispensable in navigation systems. Among its variants, single-photon LiDAR stands out for maritime applications, owing to its reduced power consumption and extended detection range. However, the high sensitivity of single-photon detectors often results in substantial noise, necessitating effective denoising before data can be utilized for identification, tracking, and other purposes. In this study, we present a novel 128-line, 1550 nm shipborne long-range single-photon LiDAR system, with data collected and analyzed in maritime environments. This system contends with challenges such as a large dynamic range, abundant noise photons, and the complexity of sea surface conditions. To address these issues, we propose an efficient and adaptive denoising algorithm based on the k-th nearest neighbor (KNN) methodology. By examining the distribution characteristics of signal and noise photons, our approach enables target extraction even under conditions of intense noise and sparse signals. Our method exhibits robust adaptability across various detection scenarios. Experimental evaluations demonstrate its efficacy, accurately identifying targets at distances of 3.2 km in clear weather and 1.6 km in foggy conditions.

HybridCBAMNet: Enhancing time series binary classification with convolutional recurrent networks and attention mechanisms

The rapid advancement of Internet of Things technology and the increasing availability of big data have resulted in an exponential growth of time series data, highlighting a pressing need for effective classification methods. This study introduces HybridCBAMNet, a novel convolutional recurrent neural network model enhanced with recurrent networks and attention mechanisms for binary time series classification. The architecture integrates Conv1D-based feature extraction modules to extract relevant features, alongside attention enhancement modules and convolutional block attention modules. Additionally, bidirectional recurrent units are utilized to capture temporal dependencies and contextual information in both forward and backward directions. The model achieves top F1-scores in seven out of thirty-six binary classification tasks, significantly surpassing the performance of fourteen existing state-of-the-art models from the UCR archive. These results demonstrate that HybridCBAMNet not only enhances classification accuracy but also improves the model generalization capabilities, contributing valuable insights to the field of time series analysis.

GIC-Flow: Appearance flow estimation via global information correlation for virtual try-on under large deformation

The primary aim of image-based virtual try-on is to seamlessly deform the target garment image to align with the human body. Owing to the inherent non-rigid nature of garments, current methods prioritise flexible deformation through appearance flow with high degrees of freedom. However, existing appearance flow estimation methods solely focus on the correlation of local feature information. While this strategy successfully avoids the extensive computational effort associated with the direct computation of the global information correlation of feature maps, it leads to challenges in garments adapting to large deformation scenarios. To overcome these limitations, we propose the GIC-Flow framework, which obtains appearance flow by calculating the global information correlation while reducing computational regression. Specifically, our proposed global streak information matching module is designed to decompose the appearance flow into horizontal and vertical vectors, effectively propagating global information in both directions. This innovative approach considerably diminishes computational requirements, contributing to an enhanced and efficient process. In addition, to ensure the accurate deformation of local texture in garments, we propose the local aggregate information matching module to aggregate information from the nearest neighbours before computing the global correlation and to enhance weak semantic information. Comprehensive experiments conducted using our method on the VITON and VITON-HD datasets show that GIC-Flow outperforms existing state-of-the-art algorithms, particularly in cases involving complex garment deformation.

Investigating the Devices that Measure and Improve Grip Strength Through Telerehabilitation: A Scoping Review

Introduction: Grip strength is a vital hand function skill required to perform everyday tasks. Diseases and conditions deteriorate grip strength. Repetitive exercises can improve grip strength, but people are non-compliant with home exercise programs. Gamification of exercises can increase home exercise compliance. A device is needed to measure and rehabilitate grip strength and to deliver exercises remotely. A preliminary search on that topic did not provide any review literature on grip-strength devices. Accordingly, this scoping literature review (SLR) explores various electronic devices and sensors used to measure grip strength. Materials and Methods: Five electronic databases, namely PubMed, IEEE, Scopus, ACM digital library, and Web of Science, were searched. Modified preferred reporting items for systematic literature review and meta-analysis guidelines were used, with population/disease, intervention, comparison, and outcome framework employed to identify keywords and frame the research questions. Results: The results of the search yielded 3546 articles, and after elimination, 15 articles met the inclusion criteria for this review. Hence, this review has categorized various devices and sensors that measured grip strength, along with their wireless communication and gamification capabilities. Conclusion: The categorization presented in this review can help researchers use this information for future directions by emphasizing research gaps and designing telerehabilitation devices.

Quantitative analysis of the contrast modulation for multilateral shearing interferometers

Multilateral shearing interferometers (multi-LSIs) utilize the phase difference information of multiple shear directions with high accuracy and strong noise resistance. However, the interferogram fringe contrast of multi-LSIs can reverse due to the effect of contrast modulation, leading to incorrect measurement result. This issue has lacked comprehensive quantitative research to effectively guide the elimination of its effects. In this work, a quantitative analysis of the contrast modulation is proposed. This paper rigorously derives contrast modulation function, analyzing the effect of aberration and shear ratio on it. It is the first time that a quantitative theoretical model of aberration measurement range and shear ratio has been established, offering guidance in practical application for precise shear ratio adjustment to eliminate modulation effect and extend measurement range. By eliminating modulation effects, phase difference information from multiple directions can be effectively utilized, maximizing the benefits of multi-LSIs. In simulation and experiment, the distribution of fringe contrast reversal bands and the variation of aberration measurement range with shear ratio are consistent with theoretical analysis, which verifies the validity of the proposed approach. This approach aims to address the issue of interferogram fringe contrast inversion caused by modulation in multi-LSIs, providing a theoretical basis and practical guidance for precise measurement.

Ethnobotanical study of medicinal plants used to manage human ailments in Lay Gaint District, South Gondar Zone, Amhara Region, Northwestern Ethiopia

The aim of this work is to document and record the use of medicinal plants to treat various ailments in the study area. A total of 84 informants, consisting of 54 men and 30 women, between 35 and 80 years of age were chosen. Additionally, 20 key informants were deliberately selected for their expertise. Data were collected through face-to-face interviews, group discussions, and guided field walks using semi-structured interview questions. Ethnobotanical data were analyzed using quantitative analytical tools such as preference ranking, direct matrix ranking, fidelity level and informant consensus factor. Forty-six medicinal plants belonging to 41 genera and 33 families were collected and identified. Brassicaceae, Ranunculaceae, and Polygonaceae had the highest abundance of medicinal plants used to treat various diseases in the study area. Most of the medicinal plants were herbs (43 %), followed by shrubs (35 %). The study revealed that leaves (45.7 %) were the most frequently used plant parts in the preparation of remedies. The most common mode of administration was oral ingestion (61 %), followed by dermal application (30 %). Zingiber officinale Roscoe and Allium sativum L.had the highest preference rank, whereas Croton macrostachyus Hochst. ex Delile was identified as the most popular medicinal plant due to its multipurpose use. while the value of fidelity level (FL) for medicinal plants in the study ranged from 34 % to 94 %. The study also identified several threats to medicinal plants in the study area, including charcoal production, overgrazing, and agricultural expansion. To prevent the eradication of these medicinal plants, the involvement of local communities in the management and conservation of plant resources is crucial.

Spatiotemporal smoothing of water quality in a complex riverine system with physical barriers

Freshwater ecosystems offer a variety of ecosystem services, and water quality is essential information for understanding their environment, biodiversity, and functioning. Interpolation by smoothing methods is a widely used approach to obtain temporal and/or spatial patterns of water quality from sampled data. However, when these methods are applied to freshwater systems, ignoring terrestrial areas that act as physical barriers may affect the structure of spatial autocorrelation and introduce bias into the estimates. In this study, we applied stochastic partial differential equation (SPDE) smoothing methods with barriers to spatial interpolation and spatiotemporal interpolation on water quality indices (chemical oxygen demand, phosphate phosphorus, and nitrite nitrogen) in a freshwater system in Japan. Then, we compared the estimation bias and accuracy with those of conventional non-barrier models. The results showed that the estimation bias of spatial interpolations of snapshot data was improved by considering physical barriers (5.8 % for (chemical oxygen demand, 22.5 % for phosphate phosphorus, and 21.6 % for nitrite nitrogen). The prediction accuracy was comparable to that of the non-barrier model. These were consistent with the expectation that accounting for physical barriers would capture realistic spatial correlations and reduce estimation bias, but would increase the variance of the estimates due to the limited information that can be gained from the neighbourhood. On the other hand, for spatiotemporal smoothing, the barrier model was comparable to the non-barrier model in terms of both estimation bias and prediction accuracy. This may be due to the availability of information in the time direction for interpolation. These results demonstrate the advantage of considering barriers when the available data are limited, such as snapshot data. SPDE smoothing methods can be widely applied to interpolation of various environmental and biological indices in river systems and are expected to be powerful tools for studying freshwater systems spatially and temporally.

Online Measurement of Melt-Pool Width in Direct Laser Deposition Process Based on Binocular Vision and Perspective Transformation.

Direct laser deposition (DLD) requires high-energy input and causes poor stability and portability. To improve the deposited layer quality, conducting online measurements and feedback control of the dimensions, temperature, and other melt-pool parameters during deposition is essential. Currently, melt-pool dimension measurement is mainly based on machine vision methods, which can mostly detect only the deposition direction of a single melt pool, limiting their measurement range and applicability. We propose a binocular-vision-based online measurement method to detect the melt-pool width during DLD. The method uses a perspective transformation algorithm to align multicamera measurements into a single-coordinate system and a fuzzy entropy threshold segmentation algorithm to extract the melt-pool true contour. This effectively captures melt-pool width information in various deposition directions. A DLD measurement system was constructed, establishing an online model that maps the melt-pool width to the offline deposited layer width, validating the accuracy of the binocular vision system in measuring melt-pool width at different deposition angles. The method achieved high accuracy for melt-pool measurements within certain deposition angle ranges. Within the 30°-60° measurement range, the average error is 0.056 mm, with <3% error. The proposed method enhances the detectable range of melt-pool widths, improving cladding layers and parts.

Simultaneous Coherent and Displacement Compounding for 2-D Noninvasive Carotid Strain Imaging: A Proof of Principle Study.

Arteriosclerosis results from lipid buildup in artery walls, leading to plaque formation, and is a leading cause of death. Plaque rupture can cause blood clots that might lead to a stroke. Distinguishing plaque types is a challenge, but ultrasound (US) elastography can help by assessing plaque composition based on strain values. Since the artery has a circular structure, an accurate axial and lateral displacement strategy is needed to derive the radial and circumferential strains. A high-precision lateral displacement is challenging due to the lack of phase information in the lateral direction of the beamformed RF data. Previously, our group has developed a compounding technique in which the lateral displacement is estimated using triangulation of the axial displacement estimated from transmitting and beamforming US beams at ±20°. However, transmitting with a single plane wave will reduce signal-to-noise and contrast-to-noise ratio as well as lateral resolution. In this article, we combine our displacement compounding with coherent compounding. Instead of transmitting a single plane wave, multiple plane waves are transmitted at certain angles centered on the angle of the beamforming grids, and then, the backscattered wavefronts are beamformed and coherently compounded on the center of the transmit beams (-20°, +20°, and 0°). The numerical investigation using the GE9LD probe ( f0 = 5.32 MHz, pitch = 230 μ m, and width = 43.9 mm) led us to 19 plane waves spanning angles within -10° to 10° (with respect to center of the transmit beams), resulting in a total of 57 plane wave transmit (for three beamforming grids at 0° and ±20°). FIELD II simulations of a cylindrically shaped phantom (mimicking the carotid artery) at a signal-to-noise ratio (SNR) ≥ 20 dB show that the proposed method decreases the root-mean-square error (RMSE) of the lateral displacement and strain estimations by 40% and 45% compared to the previous method, respectively. The results of our experiments with a carotid artery phantom [made out of 10% polyvinyl alcohol (PVA)] show that the proposed method provides strain images with higher quality and more in agreement with the theory, with 26% lower standard deviation, especially at the peak systolic phase. The proposed method paves the path toward improved quality in vivo 2-D strain imaging using our displacement compounding technique and translating it to 3-D with a row-column array.

Phase-field model for 2D cohesive-frictional shear fracture: An energetic formulation

This paper presents a phase-field model for cohesive-frictional shear fracture. The model is derived based on two energetic principles: the energy conservation law and a variational inequality of virtual work that serves as a stability condition. We show that all the governing equations for frictional fracture can be obtained from the above two principles, including the equilibrium condition, the phase-field evolution law and, most importantly, the yield function and flow rule for the plasticity-like frictional slip. The information of crack direction is naturally included in the flow rule. Theoretical and numerical results show that the proposed model is faithfully consistent with the Mohr–Coulomb theory of frictional failure in terms of the crack nucleation stress and direction. In addition, the presented phase-field model has an explicit frictional cohesive law.

Back-trajectory analyses for evaluating the transboundary transport effect to the aerosol pollution in South Korea

This study performed a back-trajectory analysis to determine the influence of transboundary transport on the extent of aerosol pollution in South Korea, based on 5-year PM2.5 measurements (2015–2019) in five cities covering South Korea. A transboundary transport case was selected if a back trajectory passed over a dedicated region (BOX 1 and BOX 2) in the Yellow Sea. First, we found that the frequency of transboundary transport largely increases in the high pollution case, and this pattern is almost consistent for all months and all five cities, indicating the importance of investigating the horizontal direction of air mass movement associated with PM2.5, which has been discussed extensively in previous studies. In this study, we also examined the altitude change and straight moving distance (defined as travel distance) of back trajectories regarding the extent of local PM2.5. Consequently, we found that back trajectories in high aerosol pollution showed much lower altitudes and shorter travel differences, implying a significant contribution of surface emissions and stagnant air conditions to severe aerosol pollution. As a result, the local PM2.5 level was not significantly enhanced when the air mass passed over the Yellow Sea if transboundary transport occurred at high altitudes with rapid movement (i.e., high altitude and long travel distance back-trajectory). Based on these results, we suggest utilizing the combined information of the horizontal direction, altitude variation, and length of back trajectories to better evaluate transboundary transport.

CapMax: A Framework for Dynamic Network Representation Learning From the View of Multiuser Communication.

In this article, a modified mutual information maximization (InfoMax) framework, named channel capacity maximization (CapMax), is proposed and applied to learn informative representations for dynamic networks with time-varying topology and/or time-evolving node attributes. The CapMax is based on the network information theory for multiuser communication, where the representation model is treated as a multiaccess communication channel with memory and feedback. Without requirements of the backbone structure, the learning objective of our CapMax is maximizing the channel capacity, which is measured by directed information (DI) rather than mutual information. For efficient implementation, we design an estimator of the channel capacity through the combination of graph neural networks (GNNs) and recurrent neural networks (RNNs). Under some mild conditions, we theoretically prove that DI is a better measure than mutual information in capturing useful information. The experiments are conducted on multiple real-world dynamic network datasets, and the outperformance of our CapMax on different backbone models on link detection and prediction validates the effectiveness of modeling the representation model as a communication channel.

Status-Aware Signed Heterogeneous Network Embedding With Graph Neural Networks.

Many real-world applications are inherently modeled as signed heterogeneous networks or graphs with positive and negative links. Signed graph embedding embeds rich structural and semantic information of a signed graph into low-dimensional node representations. Existing methods usually exploit social structural balance theory to capture the semantics of the complex structure in a signed graph. These methods either omit the node features or may discard the direction information of the links. To address these issues, we propose a new framework, called a status-aware graph neural network (S-GNN), to boost the representation learning performance. S-GNN is equipped with a loss function designed based on status theory, a social-psychological theory specifically developed for directed signed graphs. Extensive experimental results on benchmarking datasets verified that S-GNN can distill comprehensive information ingrained in a signed graph in the embedding space. Specifically, S-GNN achieves state-of-the-art accuracy, robustness, and scalability: it speeds up the processing time of link sign prediction by up to 6.5 × and increases accuracy by up to 18.8% as compared with the alternatives. We also show that S-GNN can obtain effective status scores of nodes for link sign prediction and node ranking tasks, both of which yield state-of-the-art performance.

Enhancing value creation of operational management for small to medium manufacturer: A conceptual data-driven analytical system

This paper aims to explore the challenges and opportunities for Small and Medium-sized Manufacturing Enterprises (SMMEs) in implementing data-driven techniques in their operations. SMMEs are often considered to be low and medium–low tech companies, even if they have machinery, as they still rely on traditional processes and manpower and lack any digital technology. Previous research has shown that medium–high and high-tech companies perform better, with higher rates of growth, than low and medium–low ones by a sustainable and significant margin. Therefore, there is a need for further research on the implementation of data-driven analytical methods and technologies in SMMEs that are both cost-effective and easy to use. This study proposes a conceptual analytical system that combines Integration Definition for Function Modeling 0 (IDEF0) and the Cross Industry Standard Process for Data Mining (CRISP-DM) business analytics method to develop a practical and widely applicable framework for data-driven techniques in manufacturing. We then developed a case study of an Indonesian company, where we collected real and direct information about specific objects, events, and activities related to particular aspects, including showing their key performance indicators (KPIs) through data dashboards, to evaluate the effectiveness of the proposed conceptual analytical system in improving operational management in SMMEs. The findings of this study provide valuable insights that can be used to develop effective solutions for SMMEs to leverage data-driven techniques and improve their operations. We also highlight implications of the findings for future research and practical applications. The final framework can be converted into a system that can be continuously and flexibly updated and customized, based on specific needs.

Face-Specific Activity in the Ventral Stream Visual Cortex Linked to Conscious Face Perception.

When presented with visual stimuli of face images, the ventral stream visual cortex of the human brain exhibits face-specific activity that is modulated by the physical properties of the input images. However, it is still unclear whether this activity relates to conscious face perception. We explored this issue by using the human intracranial electroencephalography technique. Our results showed that face-specific activity in the ventral stream visual cortex was significantly higher when the subjects subjectively saw faces than when they did not, even when face stimuli were presented in both conditions. In addition, the face-specific neural activity exhibited a more reliable neural response and increased posterior-anterior direction information transfer in the "seen" condition than the "unseen" condition. Furthermore, the face-specific neural activity was significantly correlated with performance. These findings support the view that face-specific activity in the ventral stream visual cortex is linked to conscious face perception.

Extracting free energies from local composition fluctuations in solids: A frequency distribution analysis of simulated atom probe data obtained by TAPSim

The present work proposes a novel methodology to extract direct thermodynamic information, i.e. Gibbs free energies, from local composition fluctuations found in atom probe data based on statistical mechanics. The proof-of-concept is demonstrated with an exemplary simulated Cu–Ni alloy, which has first been equilibrated using Monte Carlo techniques with an embedded-atom method potential and subsequently field evaporated by TAPSim. It is shown that the variance of the frequency distribution of the local composition on the reconstructed data reveals a systematic dependence on the size of the chosen spherical (sub-) volume used for the evaluation, but nevertheless the extrapolation to an infinitely large volume unveils a unique link to the curvature of the Gibbs free energy. Given the composition range is explored at several points, the Gibbs excess free energy of mixing could be recovered in a CALPHAD-style parametrization. This methodology promises to improve the accuracy of thermodynamic information (e.g. miscibility gap, mixing/demixing tendencies, critical solution temperature) from direct atom probe measurements.

Vertical-horizontal latent space with iterative memory review network for multi-class anomaly detection

Anomaly detection has been recently proposed as a visual scene understanding task and widely applied in industrial detection. Traditional unsupervised methods aim to enhance anomaly detection performance by improving input reconstruction quality. However, these approaches rarely address the problem of poor quality reconstruction information. The inferior information affects the reconstruction effect of the input images, and further weakens the recognition performance of anomaly detection. Moreover, existing methods ignore the features of generated images and information interaction between modules, resulting in insufficient use of information. In this paper, a novel Iterative Memory Review Network (IMRN) based on horizontal-vertical latent space is presented to detect anomalies by selecting prior reconstruction information and strengthening the interactivity between network modules. An iterative memory module is recommended for the generator to encode high-dimensional inputs. Meanwhile, a review module is proposed for image modeling by extracting local and global features and fusing reconstruction process information. While completing the expansion of horizontal latent space, the review module also encodes vertical information in different directions from the iterative memory module. Our proposed approach is validated in multi-class anomaly detection tasks on public datasets. Extensive experimental results on the MVTec dataset verify the superiority of our proposed IMRN.

Physics informed sound field interpolation using an acoustic sensor network

Sound field estimation is the process of analyzing and characterizing the distribution of sound waves in a particular physical space. The applications of sound field estimation extend to various areas, including the visualization of acoustic fields, interpolation of room impulse responses, identification of sound sources, capturing sound fields for spatial audio, and spatial active noise control, among other potential uses. In a previous study, a directionally weighted kernel has been used to estimate the sound field, where the priori information of source directions is employed to improve the estimation accuracy. In another separate study, spherical harmonics have been used to represent the sound field. However, the order of spherical harmonic coefficients was limited due to the limited number of microphones. This research introduces a novel method for sound field estimation using multiple microphones to sample a source-free volume. A physics-informed neural network is used to predict the spherical harmonics coefficients and locations of unknown sources to estimate the sound field.

Defect identification of bare printed circuit boards based on Bayesian fusion of multi-scale features.

The aim of this article is to propose a defect identification method for bare printed circuit boards (PCB) based on multi-feature fusion. This article establishes a description method for various features of grayscale, texture, and deep semantics of bare PCB images. First, the multi-scale directional projection feature, the multi-scale grey scale co-occurrence matrix feature, and the multi-scale gradient directional information entropy feature of PCB were extracted to build the shallow features of defect images. Then, based on migration learning, the feature extraction network of the pre-trained Visual Geometry Group16 (VGG-16) convolutional neural network model was used to extract the deep semantic feature of the bare PCB images. A multi-feature fusion method based on principal component analysis and Bayesian theory was established. The shallow image feature was then fused with the deep semantic feature, which improved the ability of feature vectors to characterize defects. Finally, the feature vectors were input as feature sequences to support vector machines for training, which completed the classification and recognition of bare PCB defects. Experimental results show that the algorithm integrating deep features and multi-scale shallow features had a high recognition rate for bare PCB defects, with an accuracy rate of over 99%.