Gastrointestinal image classification with GIDNet CNN model and non-linear Tansh activation function.

Crack detection is critical for maintaining the safety and longevity of infra-structure, yet traditional methods often rely on manual inspection or basic image pro-cessing techniques, which are labor-intensive and prone to errors. To overcome these challenges, this paper proposes a novel crack detection approach using a GOA-Unet segmentation model. The Grasshopper Optimization Algorithm (GOA) is employed to optimize the hyperparameters of the U-Net architecture, improving detection accuracy by addressing issues such as small crack detection and false positives. Furthermore, Power Law Transformation is applied to enhance image contrast, ensuring that subtle cracks are more visible. The Generative Adversarial Network (GAN) is used for data augmentation, generating realistic crack patterns to increase the diversity of the training dataset. This augmentation helps the model generalize better across various crack types and imaging conditions. Additionally, Connected Component Analysis (CCA) is utilized for aspect ratio calculation, providing detailed geometric information about the detected cracks, which is critical for assessing their structural significance. The pro-posed GOA-Unet model achieves a crack detection accuracy of 98.5% across multiple datasets, outperforming conventional models in terms of precision and generalization. These findings demonstrate that the integration of GOA, Power Law Transformation, GAN-based augmentation, and CCA offers a robust solution for accurate and efficient crack detection in real-world application. • GOA automates U-Net hyperparameter tuning for optimized crack segmentation. • GAN-based augmentation addresses data scarcity, boosting model generalization. • Power Law Transformation enhances contrast, enabling fine crack detection. • Integrated CCA extracts crack geometry for quantitative severity assessment. • Attained 98.5% accuracy rate on challenging crack identification tasks.

BCMA-MBF: Research on depression prediction based on bidirectional cross-modal attention with multi-task linear fusion.

HIV/AIDS is a serious health problem that continues to present a significant health concern in underdeveloped nations and may be mostly brought on via unprotected sex. This study is designed and analyzed using a dynamic modeling approach to investigate the dynamic of HIV/AIDS model with vertical transmission and the impact of knowledge on its treatment. Our proposed model exhibit disease free and the endemic equilibrium. The uniqueness and the exactness of the model were investigated and the basic reproduction number using next generation matrix was obtained, Stability analysis was also carried out. The model analysis shows that the disease free equilibrium is locally asymptomatically stable (LAS) when 1 0 R  . Our research suggests that treatment and awareness campaigns, when combined with other crucial control measures, may help keep the HIV/AIDS virus from spreading.

Hyperspectral image classification plays a crucial role in various remote sensing applications, requiring deep learning models that offer both high accuracy and stability. In this study, we propose “CGLM-tweaked ResNet-16”, an optimized variant of ResNet-16, demonstrating superior performance across hyperspectral datasets. Our experiments on the “Indian Pines” and “Pavia University” datasets reveal that, CGLM ResNet-16 outperforms standard ResNet-16, particularly in terms of accuracy and loss reduction. For the Indian Pines dataset, CGLM ResNet-16 achieves an impressive 99.88% accuracy with the lowest loss of 2.8%, surpassing other competing models. Similarly, for the Pavia University dataset, the model maintains low loss 0.23% while achieving competitive accuracy, signifying improved efficiency and model stability. The reduced loss values indicate better generalization and robustness, crucial for real-world applications. While the pro-posed model enhances classification performance, certain challenges persist, particularly in noise reduction across multiple layers. Future research should explore hybrid deep learning architectures to further optimize accuracy without increasing computational overhead. The biggest challenge ahead is cross domain analysis which remains a critical bottleneck in multiband image processing. Effective noise removal techniques tailored for hyperspectral imaging must be developed to enhance the model’s generalization across diverse datasets. Addressing these challenges will significantly improve real-world applications, such as remote sensing, land cover classification, and environmental monitoring. In conclusion, CGLM ResNet-16 presents a promising statistical analysis method advancement in hyperspectral image classifi-cation, offering improved accuracy and loss minimization.

The pervasive integration of Unmanned Aerial Vehicle (UAV) networks across various applications underscores the imperative for sophisticated communication and collision avoidance strategies to optimize their operational prowess. Traditional UAV network optimization methodologies grapple with inherent challenges related to collision minimization and channel utilization, resulting in detrimental outcomes such as elevated communication delays, increased energy consumption, and compromised throughput alongside diminished packet delivery ratios. This study addresses these shortcomings through the introduction of an innovative optimization model that synergizes the robust characteristics of the Teacher Learner-based Grey Wolf Optimizer (TLGWO) and the Bat Firefly Optimizer (BFFO), thereby significantly elevating the overall performance of UAV networks. The TLGWO component of the pro-posed model is intricately designed to minimize collisions among UAV nodes by analytically assessing temporal and spatial performance metrics. This includes a nuanced examination of communication delay dynamics and the historical context of avoided collisions. Simultaneously, the BFFO module is engineered to maximize channel utilization, leveraging the same performance metrics for a holistic optimization approach. The dual application of TLGWO and BFFO ensures a comprehensive enhancement of UAV network efficiency. Empirical validation demonstrates the superiority of the proposed model over existing methods, showcasing a remarkable 10.4% reduction in communication delay, an 8.5% improvement in energy efficiency, a 3.5% increase in packet delivery ratio, a 9.5% enhancement in throughput, and a 4.9% reduction in collision occurrences. The significant impact of this research is far-reaching, providing a robust and versatile framework for fortifying UAV network efficiency across diverse applications, thereby propelling the field towards more dependable and efficient UAV deployments in critical sectors.

This study considers a two-echelon supply chain (SC) consisting of a single vendor and a single buyer by reducing delivery time. This paper examines delivery time optimization as an essential component of lead times. The length of delivery time and production time are studied simultaneously. The delivery time as a decision variable is considered in the proposed model. Reducing delivery time is considered a vital incentive factor in encouraging the buyer to participate in the coordinated model to guarantee profitability. A suggested mathematical model consisting of the profit functions of both participants (i.e., vendor and buyer) are investigated under two decision-making scenarios: the decentralized decision structure and coordinated decision structure. The analyses show that our proposed model ensures better performance for both participants and makes the whole process more profitable by an adequate sharing of risks between two participants. In other words, under the coordinated model, decreasing the delivery time and buyer's shortage costs and increasing the order quantity leads to an increase in the profit of the vendor and buyer.

It is commonly known that food nutrition is closely related to human health. The complex interactions between food nutrients and diseases, influenced by gut microbial metabolism, present challenges in systematizing and practically applying knowledge. To address this, we propose a method for extracting triples from a vast amount of literature, which is used to construct a comprehensive knowledge graph on nutrition and human health. Concurrently, we develop a query-based question answering system over our knowledge graph, proficiently addressing three types of questions. The results show that our proposed model outperforms other state-of-art methods, achieving a precision of 0.92, a recall of 0.81, and an F1 score of 0.86 in the nutrition and disease relation extraction task. Meanwhile, our question answering system achieves an accuracy of 0.68 and an F1 score of 0.61 on our benchmark dataset, showcasing competitiveness in practical scenarios. Furthermore, we design five independent experiments to assess the quality of the data structure in the knowledge graph, ensuring results characterized by high accuracy and interpretability. In conclusion, the construction of our knowledge graph shows significant promise in facilitating diet recommendations, enhancing patient care applications, and informing decision-making in clinical research.

In this article, we introduce Neural-ABC, a novel parametric model based on neural implicit functions that can represent clothed human bodies with disentangled latent spaces for identity, clothing, shape, and pose. Traditional mesh-based representations struggle to represent articulated bodies with clothes due to the diversity of human body shapes and clothing styles, as well as the complexity of poses. Our proposed model provides a unified framework for parametric modeling, which can represent the identity, clothing, shape and pose of the clothed human body. Our proposed approach utilizes the power of neural implicit functions as the underlying representation and integrates well-designed structures to meet the necessary requirements. Specifically, we represent the underlying body as a signed distance function and clothing as an unsigned distance function, and they can be uniformly represented as unsigned distance fields. Different types of clothing do not require predefined topological structures or classifications, and can follow changes in the underlying body to fit the body. Additionally, we construct poses using a controllable articulated structure. The model is trained on both open and newly constructed datasets, and our decoupling strategy is carefully designed to ensure optimal performance. Our model excels at disentangling clothing and identity in different shape and poses while preserving the style of the clothing. We demonstrate that Neural-ABC fits new observations of different types of clothing. Compared to other state-of-the-art parametric models, Neural-ABC demonstrates powerful advantages in the reconstruction of clothed human bodies, as evidenced by fitting raw scans, depth maps and images. We show that the attributes of the fitted results can be further edited by adjusting their identities, clothing, shape and pose codes.

Capsule networks (CapsNets) aim to parse images into a hierarchy of objects, parts, and their relationships using a two-step process involving part-whole transformation and hierarchical component routing. However, this hierarchical relationship modeling is computationally expensive, which has limited the wider use of CapsNet despite its potential advantages. The current state of CapsNet models primarily focuses on comparing their performance with capsule baselines, falling short of achieving the same level of proficiency as deep convolutional neural network (CNN) variants in intricate tasks. To address this limitation, we present an efficient approach for learning capsules that surpasses canonical baseline models and even demonstrates superior performance compared with high-performing convolution models. Our contribution can be outlined in two aspects: first, we introduce a group of subcapsules onto which an input vector is projected. Subsequently, we present the hybrid Gromov-Wasserstein (HGW) framework, which initially quantifies the dissimilarity between the input and the components modeled by the subcapsules, followed by determining their alignment degree through optimal transport (OT). This innovative mechanism capitalizes on new insights into defining alignment between the input and subcapsules, based on the similarity of their respective component distributions. This approach enhances CapsNets' capacity to learn from intricate, high-dimensional data while retaining their interpretability and hierarchical structure. Our proposed model offers two distinct advantages: 1) its lightweight nature facilitates the application of capsules to more intricate vision tasks, including object detection; and 2) it outperforms baseline approaches in these demanding tasks. Our empirical findings illustrate that HGW capsules (HGWCapsules) exhibit enhanced robustness against affine transformations, scale effectively to larger datasets, and surpass CNN and CapsNet models across various vision tasks.

Lidars and cameras are critical sensors for 3D object detection in autonomous driving. Despite the increasing popularity of sensor fusion in this field, accurate and robust fusion methods are still under exploration due to non-homogenous representations. In this paper, we find that the complementary roles of point clouds and images vary with depth. An important reason is that the point cloud appearance changes significantly with increasing distance from the Lidar, while the image's edge, color, and texture information are not sensitive to depth. To address this, we propose a fusion module based on the Depth Attention Mechanism (DAM), which mainly consists of two operations: gated feature generation and point cloud division. The former adaptively learns the importance of bimodal features without additional annotations, while the latter divides point clouds to achieve differential fusion of multi-modal features at different depths. This fusion module can enhance the representation ability of original features for different point sets and provide more comprehensive features by using the dual splicing strategy of concatenation and index connection. Additionally, considering point density as a feature and its negative correlation with depth, we build an Adaptive Threshold Generation Network (ATGN) to generate the depth threshold by extracting density information, which can divide point clouds more reasonably. Experiments on the KITTI dataset demonstrate the effectiveness and competitiveness of our proposed models.

This article discusses the need to make the understanding of social justice in career guidance a collective task for professional communities. The article explores various understandings of social justice in career guidance and how these have been translated into frameworks for practice. Drawing on the theory of communities of practice, the article argues that a professional understanding of social justice could be developed through professional communities of practice with the aim of promoting a pluralism of understandings, not an ultimate consensus. Finally, the article presents a proposed model for such work.

High-frequency trading proposes new challenges to classical portfolio selection problems. Especially, the timely and accurate solution of portfolios is highly demanded in financial market nowadays. This article makes progress along this direction by proposing novel neural networks with softmax equalization to address the problem. To the best of our knowledge, this is the first time that softmax technique is used to deal with equation constraints in portfolio selections. Theoretical analysis shows that the proposed method is globally convergent to the optimum of the optimization formulation of portfolio selection. Experiments based on real stock data verify the effectiveness of the proposed solution. It is worth mentioning that the two proposed models achieve 5.50% and 5.47% less cost, respectively, than the solution obtained by using MATLAB dedicated solvers, which demonstrates the superiority of the proposed strategies.

Background: With new variants of COVID-19 causing challenges, we need to focus on integrating multiple deep-learning frameworks to develop intelligent healthcare systems for early detection and diagnosis. Objective: This article suggests three hybrid deep learning models, namely CNN-LSTM, CNN-Bi- LSTM, and CNN-GRU, to address the pressing need for an intelligent healthcare system. These models are designed to capture spatial and temporal patterns in COVID-19 data, thereby improving the accuracy and timeliness of predictions. An output forecasting framework integrates these models, and an optimization algorithm automatically selects the hyperparameters for the 13 baselines and the three proposed hybrid models. Methods: Real-time time series data from the five most affected countries were used to test the effectiveness of the proposed models. Baseline models were compared, and optimization algorithms were employed to improve forecasting capabilities. Results: CNN-GRU and CNN-LSTM are the top short- and long-term forecasting models. CNNGRU had the best performance with the lowest SMAPE and MAPE values for long-term forecasting in India at 3.07% and 3.17%, respectively, and impressive results for short-term forecasting with SMAPE and MAPE values of 1.46% and 1.47%. Conclusion: Hybrid deep learning models, like CNN-GRU, can aid in early COVID-19 assessment and diagnosis. They detect patterns in data for effective governmental strategies and forecasting. This helps manage and mitigate the pandemic faster and more accurately.

Recently, deep learning-based compressed sensing (CS) has achieved great success in reducing the sampling and computational cost of sensing systems and improving the reconstruction quality. These approaches, however, largely overlook the issue of the computational cost; they rely on complex structures and task-specific operator designs, resulting in extensive storage and high energy consumption in CS imaging systems. In this article, we propose a lightweight but effective deep neural network based on recurrent learning to achieve a sustainable CS system; it requires a smaller number of parameters but obtains high-quality reconstructions. Specifically, our proposed network consists of an initial reconstruction sub-network and a residual reconstruction sub-network. While the initial reconstruction sub-network has a hierarchical structure to progressively recover the image, reducing the number of parameters, the residual reconstruction sub-network facilitates recurrent residual feature extraction via recurrent learning to perform both feature fusion and deep reconstructions across different scales. In addition, we also demonstrate that, after the initial reconstruction, feature maps with reduced sizes are sufficient to recover the residual information, and thus we achieved a significant reduction in the amount of memory required. Extensive experiments illustrate that our proposed model can achieve a better reconstruction quality than existing state-of-the-art CS algorithms, and it also has a smaller number of network parameters than these algorithms. Our source codes are available at: <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/C66YU/CSRN</uri> .

A core aim of neurocritical care is to prevent secondary brain injury. Spreading depolarizations (SDs) have been identified as an important independent cause of secondary brain injury. SDs are usually detected using invasive electrocorticography recorded at high sampling frequency. Recent pilot studies suggest a possible utility of scalp electrodes generated electroencephalogram (EEG) for non-invasive SD detection. However, noise and attenuation of EEG signals makes this detection task extremely challenging. Previous methods focus on detecting temporal power change of EEG over a fixed high-density map of scalp electrodes, which is not always clinically feasible. Having a specialized spectrogram as an input to the automatic SD detection model, this study is the first to transform SD identification problem from a detection task on a 1-D time-series wave to a task on a sequential 2-D rendered imaging. This study presented a novel ultra-light-weight multi-modal deep-learning network to fuse EEG spectrogram imaging and temporal power vectors to enhance SD identification accuracy over each single electrode, allowing flexible EEG map and paving the way for SD detection on ultra-low-density EEG with variable electrode positioning. Our proposed model has an ultra-fast processing speed (<0.3 sec). Compared to the conventional methods (2 hours), this is a huge advancement towards early SD detection and to facilitate instant brain injury prognosis. Seeing SDs with a new dimension - frequency on spectrograms, we demonstrated that such additional dimension could improve SD detection accuracy, providing preliminary evidence to support the hypothesis that SDs may show implicit features over the frequency profile.

Graph neural network (GNN) is a robust model for processing non-Euclidean data, such as graphs, by extracting structural information and learning high-level representations. GNN has achieved state-of-the-art recommendation performance on collaborative filtering (CF) for accuracy. Nevertheless, the diversity of the recommendations has not received good attention. Existing work using GNN for recommendation suffers from the accuracy-diversity dilemma, where slightly increases diversity while accuracy drops significantly. Furthermore, GNN-based recommendation models lack the flexibility to adapt to different scenarios' demands concerning the accuracy-diversity ratio of their recommendation lists. In this work, we endeavor to address the above problems from the perspective of aggregate diversity, which modifies the propagation rule and develops a new sampling strategy. We propose graph spreading network (GSN), a novel model that leverages only neighborhood aggregation for CF. Specifically, GSN learns user and item embeddings by propagating them over the graph structure, utilizing both diversity-oriented and accuracy-oriented aggregations. The final representations are obtained by taking the weighted sum of the embeddings learned at all layers. We also present a new sampling strategy that selects potentially accurate and diverse items as negative samples to assist model training. GSN effectively addresses the accuracy-diversity dilemma and achieves improved diversity while maintaining accuracy with the help of a selective sampler. Moreover, a hyper-parameter in GSN allows for adjustment of the accuracy-diversity ratio of recommendation lists to satisfy the diverse demands. Compared to the state-of-the-art model, GSN improved R @20 by 1.62%, N @20 by 0.67%, G @20 by 3.59%, and E @20 by 4.15% on average over three real-world datasets, verifying the effectiveness of our proposed model in diversifying overall collaborative recommendations.

Over recent years, a number of knowledge graphs (KGs) have emerged. Nevertheless, a KG can never reach full completeness. A viable approach to increase the coverage of a KG is KG alignment (KGA). The majority of previous efforts merely focus on the matching between entities, while largely neglect relations. Besides, they heavily rely on labeled data, which are difficult to obtain in practice. To address these issues, in this work, we put forward a general framework to simultaneously align entities and relations under scarce supervision. Our proposal consists of two main components, relation-enhanced active instance selection (RAS), and cross-view contrastive learning (CCL). RAS aims to select the most valuable instances to be labeled with the guidance of relations, while CCL contrasts cross-view representations to augment scarce supervision signals. Our proposal is agnostic to the underlying entity and relation alignment models, and can be used to improve their performance under limited supervision. We conduct experiments on a wide range of popular KG pairs, and the results demonstrate that our proposed model and its components can consistently boost the alignment performance under scarce supervision.

The augmented Sylvester equation, as a comprehensive equation, is of great significance and its special cases (e.g., Lyapunov equation, Sylvester equation, Stein equation) are frequently encountered in various fields. It is worth pointing out that the current research on simultaneously eliminating the lagging error and handling noises in the nonstationary complex-valued field is rather rare. Therefore, this article focuses on solving a nonstationary complex-valued augmented Sylvester equation (NCASE) in real time and proposes two modified recurrent neural network (RNN) models. The first proposed modified RNN model possesses gradient search and velocity compensation, termed as RNN-GV model. The superiority of the proposed RNN-GV model to traditional algorithms including the complex-valued gradient-based RNN (GRNN) model lies in completely eliminating the lagging error when employed in the nonstationary problem. The second model named complex-valued integration enhanced RNN-GV with the nonlinear acceleration (IERNN-GVN) model is proposed to adapt to a noisy environment and accelerate the convergence process. Besides, the convergence and robustness of these two proposed models are proved via theoretical analysis. Simulative results on an illustrative example and an application to the moving source localization coincide with the theoretical analysis and illustrate the excellent performance of the proposed models.

Joint entity and relation extraction is an important task in natural language processing, which aims to extract all relational triples mentioned in a given sentence. In essence, the relational triples mentioned in a sentence are in the form of a set, which has no intrinsic order between elements and exhibits the permutation invariant feature. However, previous seq2seq-based models require sorting the set of relational triples into a sequence beforehand with some heuristic global rules, which destroys the natural set structure. In order to break this bottleneck, we treat joint entity and relation extraction as a direct set prediction problem, so that the extraction model is not burdened with predicting the order of multiple triples. To solve this set prediction problem, we propose networks featured by transformers with non-autoregressive parallel decoding. In contrast to autoregressive approaches that generate triples one by one in a specific order, the proposed networks are able to directly output the final set of relational triples in one shot. Furthermore, we also design a set-based loss that forces unique predictions through bipartite matching. Compared with cross-entropy loss that highly penalizes small shifts in triple order, the proposed bipartite matching loss is invariant to any permutation of predictions; thus, it can provide the proposed networks with a more accurate training signal by ignoring triple order and focusing on relation types and entities. Various experiments on two benchmark datasets demonstrate that our proposed model significantly outperforms the current state-of-the-art (SoTA) models. Training code and trained models are now publicly available at https://github.com/DianboWork/SPN4RE.