Search

Medical images acquired at different institutions have different data distributions due to varying scanners, imaging protocols, or patient cohorts. Thus, normalizing samples before using them to train the Deep Learning (DL) models is an essential task. Scholars have used various normalization methods to normalize mammograms. However, which normalization method works best on mammograms and if it can help training generalize the DL model has not been analyzed in the literature. This paper presents a comparative analysis of commonly used normalization methods, such as scaling, Contrast Limited Adaptive Histogram Equalization (CLAHE), and Z-score normalization on mammograms for breast mass segmentation tasks. We trained the Attention Unet model on INbreast and the subset of the Cohort of Screen-Aged Women dataset (CSAW-S). We performed cross-dataset analysis on trained models to investigate how normalization methods helped train robust models to handle diverse datasets. Our results suggest that the normalizing method of input data affects the segmentation model's performance. We achieved the best scores with the Z-score normalization closely followed by CLAHE. However, further investigation suggests that the normalization method's performance may depend on the variability of mammograms in the dataset. Results of cross-dataset analysis suggest the importance of choosing the normalization method for consistent DL model performance. To our knowledge, this study represents the first systematic analysis of the performance of prevalent normalization techniques on a diverse dataset of mammogram images. The insights gained from our experiments can guide the selection of normalization methods for improved mass segmentation accuracy. [ABSTRACT FROM AUTHOR]

This paper aims to address two significant challenges of Deep Learning(DL) model generation, high computational cost involved during the training phase and data interpretability from high dimensional data. The computational cost is curbed using centralized as well as distributed matrix factorization technique known as CUR decomposition. CUR decomposition has the advantage of reducing the dimensions of the dataset without data transformation and minimal information loss. Though Singular Value De-composition(SVD) is the best matrix decomposition technique with least reconstruction error, it transforms the data and hence the original data cannot be interpreted from the decomposed matrices while applying DL technique. So CUR decomposition is leveraged to reduce the number of features in high-dimensional data while preserving the essential information. Extensive experimental analysis is conducted to evaluate and compare the performance of CUR and SVD techniques based on reconstruction error and time complexity in centralized as well as distributed setting. The results exhibit that CUR outperforms SVD in terms of computational efficiency, especially in a distributed setting where the decomposition time for CUR was a fraction compared to SVD. At the same time DL models generated from this reduced dataset exhibit comparable accuracy with the original high dimensional dataset as well as reduced dataset obtained through SVD. This work also enhances the accessibility of the CUR algorithm to users, for which an application is developed that enables users to execute the algorithm on any dataset. The user-friendly interface of the application facilitates the upload of datasets, configuration of desired decomposition rank, and execution of the algorithm with a single click. [ABSTRACT FROM AUTHOR]

Object detection is a basic vision task that accompanies people's daily lives all the time. The development of object detection technology has experienced an evolution from traditional-based algorithms to deep learning-based algorithms, which has made a qualitative leap in both detection accuracy and detection speed. With the advancement of deep learning, object detection techniques are increasingly becoming a part of everyday life, with the YOLO series of algorithms being extensively applied in various industries. In this paper, we initially present the frequently utilized datasets and evaluation criteria for object detection. Subsequently, we delve into the evolution of traditional object detection algorithms, highlighting two-stage and one-stage approaches through illustrative examples of classical methods. We also conduct a comprehensive summary and analysis of the detection results obtained by these methods. In addition, we introduce object detection applications in daily life, as well as the importance and some difficulties of these applications. Finally, we analyze and summarize the difficulties and challenges facing the task of object detection, and we look forward to the future development direction of object detection. • This survey is an extended version of our paper in ICIC2023. • We review the development and challenges of object detection. • We present the application of object detection and make prospects for the future. [ABSTRACT FROM AUTHOR]

Systems that can transform two-dimensional (2D) sketches into 3D models while performing structural analyses are necessary for architectural sketches. To address this challenge, this paper focuses on how deep-learning algorithms can aid in this transformation process. It presents a model that uses the instance-segmentation technique with Mask RCNN to detect and distinguish two types of short beams of reciprocal frame structures (RFs) in 2D sketches and uses this information in the systematic creation of a 3D model of RFs to conduct their structural analysis. The results indicate that the model is capable of clustering beam types in 2D sketches via masking and classifying, eliminating irrelevant background objects, creating parametric RFs using masking information, and performing structural analysis. The model, which helps optimise and ease the design process, can be used by architects or engineers. This paper will inspire future work on the creation of integrated modelling systems. • 2D sketches database has been prepared. • Mask RCNN algorithm has been trained with the prepared database. • The trained network has been used for the proposed model. • The proposed model creates 3D RFs from 2D sketches. • The proposed model makes structural analysis of the created RFs. [ABSTRACT FROM AUTHOR]

• This paper proposed a comprehensive framework for parametric semi-automatic BIM and bridge member segmentation. • The parametric algorithm accounted for diverse types of bridge members and produced BIM bridge models using shape information automatically extracted per parameter. • The parametrically generated bridge BIM model was converted into PCD, serving as deep learning train data for automatic segmentation of bridge members. • The trained deep learning model showed high accuracy for segmenting superstructures, indicating promise for automated segmentation of bridge members. • The segmentation accuracy increased when accounting for the point density of members corresponding to the different sizes of bridge members. This paper proposes a comprehensive framework for parametric semi-automatic BIM and bridge member segmentation. For this, a parametric algorithm was developed to accommodate diverse superstructures, piers, abutments, and bearings. Each structural member in a bridge was classified to designate its shape information as parameters. The range of each parameter was defined to account for various dimensions of the shape of the bridge member. Therefore, libraries for each member were established to produce BIM bridge models using shape information automatically extracted per parameter. Then, the framework includes an algorithm that is developed to convert bridge BIM models generated by the parametric algorithm into PCD data. The virtually generated PCD is used as deep learning train data for automatic member segmentation based on the Point-Net algorithm. The trained algorithm using the virtual PCD was applied to a real bridge PCD. The segmentation of the bridge members showed high accuracy for the superstructure but low accuracy for the bearing. The segmentation accuracy of the algorithm including the bearing member could increase by modifying the density of PCD to account for the different sizes of bridge members. Furthermore, the proposed framework was applied to a UK bridge PCD and showed its applicability for use in bridges in different countries. [ABSTRACT FROM AUTHOR]

• The gated recurrent unit algorithm with fused attention mechanism is a target positioning method in a non-line-of-sight error environment. • The introduction of the attention mechanism can analyze features, select important features, and better handle non-line-of-sight errors. • Introducing the dropout layer during training reduces the risk of overfitting during training. • Through simulation and actual measurement experiments, the effectiveness of the algorithm in this paper is verified by comparing it with other famous algorithms. Amidst the increasing reliance on indoor positioning in areas such as large shopping malls, airports, and train stations, the precision of ultra-wideband (UWB) technology stands out for its centimeter-level accuracy. However, non-line-of-sight (NLOS) errors caused by people's movements significantly reduce indoor positioning accuracy. In response, this paper presents an innovative blend of gated recurrent unit algorithm with fused attention mechanism (GRU_Attention). This algorithm adeptly captures the dynamism in UWB signals and intelligently focuses on pivotal features to actualize accurate three-dimensional positioning while effectively reducing NLOS error. It has been demonstrated that GRU_Attention algorithm can reach 5.6 cm accuracy level through experiments, which improved by 74.47 %, 87.44 %, 14.46 %, 43.82 %, and 29.07 % respectively compared with the backpropagation (BP), least square (LS), GRU, convolutional neural network (CNN), and fused attention mechanism convolutional neural network (CNN_Attention) algorithms. This algorithm charts a new pathway to overcome NLOS errors in indoor personnel movement scenes. [ABSTRACT FROM AUTHOR]

This comprehensive review focuses on the Autonomous Driving System (ADS), which aims to reduce human errors that are the reason for about 95% of car accidents. The ADS consists of six stages: sensors, perception, localization, assessment, path planning, and control. We explain the main state-of-the-art techniques used in each stage, analyzing 275 papers, with 162 specifically on path planning due to its complexity, NP-hard optimization nature, and pivotal role in ADS. This paper categorizes path planning techniques into three primary groups: traditional (graph-based, sampling-based, gradient-based, optimization-based, interpolation curve algorithms), machine and deep learning, and meta-heuristic optimization, detailing their advantages and drawbacks. Findings show that meta-heuristic optimization methods, representing 23% of our study, are preferred for being general problem solvers capable of handling complex problems. In addition, they have faster convergence and reduced risk of local minima. Machine and deep learning techniques, accounting for 25%, are favored for their learning capabilities and fast responses to known scenarios. The trend towards hybrid algorithms (27%) combines various methods, merging each algorithm's benefits and overcoming the other's drawbacks. Moreover, adaptive parameter tuning is crucial to enhance efficiency, applicability, and balancing the search capability. This review sheds light on the future of path planning in autonomous driving systems, helping to tackle current challenges and unlock the full capabilities of autonomous vehicles. [ABSTRACT FROM AUTHOR]

This paper presents an adaptive and new region proposal algorithm for generating high-quality regions. The main aim of this algorithm is to investigate different features in the proposal generation process. This algorithm is based on bottom-up image segmentation and deep learning techniques. Each primary region is represented by features derived from a convolutional neural network (CNN). The adjacent and similar regions are merged based on a new proposed searching algorithm and a distance function in a hierarchical way. Additionally, various hand-crafted texture features are examined for representing each region. These texture features are not being utilized previously in region proposal generation. This method also applied both texture-based and deep learning-based features, contemporaneously. Furthermore, the proposed region proposal algorithm was evaluated on two significant challenging datasets, including VOC2012 and COCO2017. The resulting proposals show more high-quality regions in high overlaps in comparison to previous region proposal algorithms. More importantly, the results verified that the deep learning-based features together with handcrafted texture features are complement and this fusion can overcome the shortcoming of other approaches. Additionally, the proposed region proposal algorithm is employed in weakly supervised semantic segmentation. The new generated proposals are used to create some new labeled masks. These masks are very useful and effective in the training phase of deep learning. This approach is evaluated on VOC2012 and compared with previous region-based and free region-based methods. The results show the efficacy of the proposed method. • This paper proposes a new region proposal generation based on a hierarchical deep learning-based merging algorithm. • The effectiveness and quality of some known texture-based descriptors are explored in the proposed algorithm. • A new algorithm is introduced to generate pseudo training data using weak supervision and region proposal. • The proposed region proposal algorithm was evaluated on two significant challenging datasets, including VOC2012 and COCO2017. [ABSTRACT FROM AUTHOR]

Intelligent Fault-Tolerant Control (IFTC) refers to the applications of machine learning algorithms for fault diagnosis and design of Fault-Tolerant Control (FTC). The overall goal of the FTC is to accommodate defects in the system components while they are in use and maintain stability with little to no performance reduction. These systems are crucial for mission-critical and safety-related applications where the safety of people is at stake and service continuity is crucial. In this review paper, a systematic study has been done for the development of FTC with machine learning, deep learning, and transfer learning algorithms. The challenges and limitations faced with their possible solutions through machine learning theories for the IFTC model are lined up. This paper guides researchers on the different possible types of machine learning algorithms and their advanced forms like deep learning and transfer learning. The differences among these are highlighted by the challenges and limitations of each. The paper is significant such that most of the important literature references from the Scopus database particularly related to important electrical and mechanical industrial problems have been discussed to guide the researchers who want to apply IFTC for specific industrial problems, being the research gap. Finally, future research directions for the development of IFTC are highlighted. [ABSTRACT FROM AUTHOR]

Deep image clustering networks have the capability to categorize unlabeled images, thereby effectively utilizing them. This paper synthesizes recent researches about deep image clustering network and summarizes them within a general framework. Image Preprocessing part transforms collected images into a dataset accepted by the network, then Image Embedding part embeds images from the dataset into vectors which represents image features. After Feature Processing part further reduces the dimensionality or enhances these features, the following Feature Clustering part divides the images into several categories. Cluster Result Processing part treats the clustering outcomes to implement weighted, multi-view, subspace, multimodal, or self-supervised methods. Downstream Applications part employ the clustering results to address various real-world problems. The performance of common baseline clustering methods and several feature extraction architectures are also compared and analyzed. The results indicate that within deep image clustering networks, the choice of clustering algorithm has a relatively minor impact on clustering performance, whereas the selection of the feature extraction network architecture is decisive for clustering metrics. The choice of architecture should be customized based on the characteristics of the dataset. Finally, we provide suggestions for potential research directions in deep image clustering networks. • Analyzes deep image clustering theory, its performance benefits, and limitations. • Summarizes recent deep image clustering improvements with experimental data analysis. • Introduces deep image clustering applications and future improvement prospects. [ABSTRACT FROM AUTHOR]

Adversarial sample generation problem is a hot issue in the security field of deep learning. Evolutionary algorithm has been widely used to solve this problem in recent years because of its good global search ability. However, existing methods still suffer from the "curse of dimensionality" when attacking high-resolution images. In this paper, a two-stage frequency domain generation algorithm of black-box adversarial samples based on differential evolution is proposed. In the first stage, a representative image-guided differential evolution method is proposed to quickly generate a universal adversarial perturbation with a high attack success rate in the frequency-domain. In the second stage, a space reduction strategy based on frequency-domain pixel blocks is designed to reduce the search space and alleviate the problem of "curse of dimensionality". In addition, a new space–frequency interaction sensitivity measure is introduced to evaluate the similarity between the adversarial samples and the original images. The adversarial perturbations obtained by the measure are more in line with the subjective perception of the human eye. Finally, compared with several typical black-box adversarial sample generation algorithms, experimental results show that the proposed algorithm can achieve higher attack success rate with less prediction times. • Proposing a two-stage evolutionary generation framework of adversarial samples. • Developing a space–frequency interaction sensitivity measure. • Presenting a representative image-guided differential evolutionary algorithm. • Designing an individual adversarial perturbation generation algorithm. [ABSTRACT FROM AUTHOR]

• Obtained a lightweight model by designing a streamlined network structure. • Improved the average detection accuracy of the model while keeping it lightweight. • This lightweight model performs exceptionally well on embedded edge devices. Infrared-based road scene object detection algorithms often face issues with excessive parameters and computational demands, making them incompatible with edge devices having constrained computational capabilities. This paper introduces an enhanced lightweight infrared-based road object detection algorithm based on YOLOv8n. Firstly, a streamlined network architecture is devised by merging YOLOv8n's C2f module with PConv, creating a lighter module and reducing the neural network's downsampling rate of infrared images. This strategy reduces redundant computations and memory access, preventing the loss of fine details in infrared images caused by deep convolutional neural networks. Additionally, the model's accuracy in detecting infrared targets is significantly enhanced through the integration of the coordinate attention mechanism. Finally, replacing CIoU with Wise-IoU for bounding box regression in YOLOv8n accelerates the model's convergence. Empirical findings indicate that in contrast to the YOLOv8n algorithm, the optimized model showcases a 34.17 % reduction in model size, a 40.35 % decrease in parameters, and a 4.8 % increase in average detection accuracy. This enhanced algorithm not only achieves a lightweight profile but also delivers superior performance on embedded edge devices. [ABSTRACT FROM AUTHOR]

With rising data security concerns, privacy preserving machine learning (ML) methods have become a key research topic. Federated learning (FL) is one such approach which has gained a lot of attention recently as it offers greater data security in ML tasks. Substantial research has already been done on different aggregation methods, personalized FL algorithms etc. However, insufficient work has been done to identify the effects different model update strategies (concurrent FL, incremental FL, etc.) have on federated model performance. This paper presents results of extensive FL simulations run on multiple datasets with different conditions in order to determine the efficiency of 4 different FL model update strategies: concurrent, semi-concurrent, incremental, and cyclic-incremental. We have found that incremental updating methods offer more reliable FL models in cases where data is distributed both evenly and unevenly between edge nodes, especially when the number of data samples across all edge nodes is small. • Federated learning model performance is influenced by multiple environmental factors. • Different update strategies react differently to dataset size and participant number. • Update strategies can be categorized into incremental and concurrent. • Strategy selection can help inter-institutional collaboration achieve better results. • Incremental modes are more robust to lack of data. [ABSTRACT FROM AUTHOR]

In recent years, the application of deep neural networks in the field of image classification has become increasingly widespread. However, existing researches have exposed the inherent vulnerabilities and opacity of these network models, rendering them susceptible to carefully crafted adversarial attacks. This poses significant security risks to their practical deployment. Given that the majority of models in real-world applications operate in a black-box manner, current research on black-box attacks targeting classification models remains inadequate, facing significant challenges such as incomplete robustness evaluations, low success rates of black-box attacks, and excessive resource consumption during the attack process. To address these challenges, this paper innovatively proposes a black-box attack algorithm based on a cycle-consistent generative network. This algorithm directly generates adversarial perturbations through a generative network that integrates an attention mechanism, deeply learning the complex relationship between adversarial samples and clean sample data. It supports both targeted and untargeted attack modes. Experimental validation on the SAT dataset demonstrates that our method achieves an average white-box attack success rate exceeding 96% in classification tasks and an average success rate of up to 69.4% in black-box transfer attacks, exhibiting excellent transferability across different models. This research contributes significantly to enhancing the effectiveness of black-box attacks, reducing attack costs, and providing novel ideas and methods for enhancing the security of deep learning models. • We proposed an optimized cycle-consistent generative network for adversarial attacks, ultimately enhancing the success rate against other diverse black-box models. • Our algorithm offers support for both targeted and non-targeted attacks. Our targeted approach confers directionality to the generated perturbations, enabling purposeful attacks tailored to the attacker's intentions. • A transformation distribution module is incorporated into our model. We introduce a distance loss function to our overall loss computation. • Our approach enables migration attacks across different models, achieving a black-box attack success rate superior to current methods, exceeding 69.4%. [ABSTRACT FROM AUTHOR]

Raman spectroscopy is a general and non-destructive detection technique that can obtain detailed information of the chemical structure of materials. In the past, when using chemometric algorithms to analyze the Raman spectra of mixtures, the challenges of complex spectral overlap and noise often limited the accurate identification of components. The emergence of deep learning has introduced a novel approach to qualitative analysis of mixed Raman spectra. In this paper, we propose a deep learning-based Raman spectroscopy qualitative analysis algorithm (RST) by borrowing the ideas of convolutional neural network and Transformer. By transforming the Raman spectrum into 64 word vectors, the contribution weights of each word vector to the components are obtained. For the 75 spectral data used for validation, the positive identification rate can reach 100.00 %, the recall rate can reach 99.3 %, the average identification score can reach 9.51, and it is applicable to the fields of Raman and surface-enhanced Raman spectroscopy. Furthermore, compared with traditional CNN models, RST has excellent accuracy and robustness in identifying components in complex mixtures. The model's interpretability has been enhanced, aiding in a deeper understanding of spectroscopic learning patterns for future analysis of more complex mixtures. [Display omitted] • Obtaining contribution weights for Raman spectra in different bands, the network exhibits strong interpretability. • Applicable in both Raman and surface-enhanced Raman spectroscopy fields. • Strong generalization ability, resistant to interference, and minimally affected by baseline noise. [ABSTRACT FROM AUTHOR]

The removal of shadows from images is a classic problem in computer vision, aiming to restore the lighting in shadowed areas, thereby reducing the information interference and loss caused by the presence of shadows. In recent years, numerous excellent shadow removal algorithms have emerged, particularly with the rapid development of deep learning technology, which has disrupted traditional physics-based approaches and significantly improved the effectiveness of shadow removal. In this paper, we conduct a comprehensive survey of shadow removal methods published from 2017 to the present. We first introduce background knowledge about image shadow removal, providing detailed explanations of both physics-based and learning-based shadow removal methods. We analyze and compare these algorithms from both quantitative and qualitative perspectives, reassessing all models that provided open-source result sets according to uniform criteria. Additionally, we introduce commonly used datasets and evaluation metrics in the field. Finally, we discuss applications of shadow removal in specific scenarios, along with research challenges and opportunities in this domain. • Surveys taxonomy of recently image shadow removal techniques, datasets and performance metrics. • Systematic quantitative evaluations are summarized. • The impacts, applications and importance of shadow removal are explored. • Challenges and future direction are explored and analyzed. [ABSTRACT FROM AUTHOR]

• Rainbow signal inversion algorithm based on ResNet and multi-objective regression. • The algorithm is comparable in accuracy to traditional ones but three times faster. • The structure and hyperparameters of the algorithm are determined in detail. • Loss competition relationship between droplet size and refractive index is studied. • An experimental validation system was built to verify the generalizability. Traditional standard rainbow inversion algorithms for retrieving droplet size and refractive index require time-consuming complex data pre-processing and multiple calculations, while optimized. This paper proposes a novel standard rainbow signal inversion algorithm based on residual networks and multi-objective regression. The algorithm requires only simple data pre-processing and is tested on a simulated data set covering representative signals from droplets with refractive indices of 1.33–1.35 and sizes of 60–240 μm. The average absolute error of the refractive index and average relative error of the droplet size are 9.16 × 10−5 and 0.55%, respectively. Experimental validations were carried under laboratory conditions on streams of mondisperse droplets and the robustness of the algorithm was verified under two conditions. In addition to its satisfactory inversion accuracy, the speed of each signal inversion is three times faster than traditional algorithms. The proposed algorithm meets the requirements of engineering applications and scientific research in terms of accuracy and real-time performance. [ABSTRACT FROM AUTHOR]

• Precision agriculture method applicable to remote on-tree pomegranate pixel-based fruit size monitoring. • Comparison of Deep Learning and zero-shot vision Transformer instance segmentation models. • Image-Based size estimation algorithm for occluded fruits with protuberances. In situ automatic fruit monitoring is of great interest for more accurate and cost-efficient decision making in agriculture. For this purpose, the development of computer vision-based tools is essential. Deep Learning techniques have shown good performance in fruit detection and segmentation. Recently, new models based on Transformer architecture have emerged with promising potential and zero-shot inference capability. In this paper, a Deep Learning model, Mask R-CNN, was trained for on-tree pomegranate fruit segmentation and compared with foundational models based on Vision Transformer, Grounding DINO and Segment Anything Model. Results with Mask R-CNN proved a better performance, according to F1 score and AP metrics, and a lower computational cost, according to prediction time. One of the most interesting derived applications from fruit segmentation is fruit size estimation. However, segmented fruit masks are frequently incomplete due to occlusions. Therefore, image fruit size estimation is not a straightforward process. In this work, we also propose a novel algorithm to estimate and monitor the fruit size in pixel units from the automated masks. A median relative error of 1.39% was obtained, demonstrating the potential and feasibility of future fully-automatic fruit size estimators. [ABSTRACT FROM AUTHOR]

• Differential privacy and deep learning are combined to alleviate the problem of model privacy leakage. • Differential evolution is used to optimize the learning rate, accelerate the model convergence, and avoid the privacy loss. • The particle swarm optimization method is used to find the optimal weight that satisfies the privacy. • The algorithm in this paper is verified on three data sets, and the accuracy and efficiency are better. In deep learning differential privacy protection, adding noise based on gradient has become a mainstream algorithm, but excessive gradient perturbation noise causes accuracy degradation. To solve this problem, a differential privacy protection algorithm based on differential evolution and particle swarm optimization is proposed to realize hyperparameter optimization in differential privacy, reduce the impact of noise on the model, and effectively improve the accuracy. On the one hand, the differential evolution scheme performs selection, crossover and mutation on learning rate η , make it approach the global optimal solution, and improve the computational efficiency of the algorithm. On the other hand, the particle swarm optimization scheme is adopted. Without changing the parameters and gradient structure, the parameters are optimized by using the network propagation attributes, which reduces the influence of noise on the accuracy. Experiments are performed on three datasets: Cifar10, Mnist and FashionMnist. Compared with the existing differential privacy algorithms, under the same privacy budget, the proposed algorithm has better accuracy and higher efficiency. [ABSTRACT FROM AUTHOR]

Metastatic femoral tumors may lead to pathological fractures during daily activities. A CT-based finite element analysis of a patient's femurs was shown to assist orthopedic surgeons in making informed decisions about the risk of fracture and the need for a prophylactic fixation. Improving the accuracy of such analyses ruqires an automatic and accurate segmentation of the tumors and their automatic inclusion in the finite element model. We present herein a deep learning algorithm (nnU-Net) to automatically segment lytic tumors within the femur. A dataset consisting of fifty CT scans of patients with manually annotated femoral tumors was created. Forty of them, chosen randomly, were used for training the nnU-Net, while the remaining ten CT scans were used for testing. The deep learning model's performance was compared to two experienced radiologists. The proposed algorithm outperformed the current state-of-the-art solutions, achieving dice similarity scores of 0.67 and 0.68 on the test data when compared to two experienced radiologists, while the dice similarity score for inter-individual variability between the radiologists was 0.73. The automatic algorithm may segment lytic femoral tumors in CT scans as accurately as experienced radiologists with similar dice similarity scores. The influence of the realistic tumors inclusion in an autonomous finite element algorithm is presented in (Rachmil et al., "The Influence of Femoral Lytic Tumors Segmentation on Autonomous Finite Element Analyses", Clinical Biomechanics, 112, paper 106192, (2024)). • A deep learning algorithm for automatic segmentation of lytic femoral tumors is developed. • The deep learning dice similarity score of ∼0.67 is obtained, higher than any former study. • Inter-individual dice similarity score variability between two radiologists was 0.73. • The automatic segmentation of lytic tumors is as good as a radiologist. [ABSTRACT FROM AUTHOR]

An important objective in computer vision is to analyze multiple images and subsequently reconstruct the shape and structure in 3D. Traditional multi-view 3D reconstruction techniques extract and match key features from images with known camera parameters. However, this approach is inefficient and fails to fully exploit the advantages of multi-view information. Advancements in deep learning have revolutionized multi-view 3D reconstruction by enabling end-to-end 3D shape inferencing without the need for sequential feature matching typically found in conventional algorithms. Recent rapid progress in this field necessitates a thorough review of current algorithms and provide insight into method of improving 3D reconstruction performance. This review classifies reconstruction algorithms according to their resultant model, including depth map, voxel, point cloud, mesh, and implicit surface. Additionally, this review encompasses the inclusion of frequently employed network training loss functions for network training, assessment metrics, and the incorporation of 3D datasets. Experimental results are also presented to assess the performance of different algorithms. Finally, the paper concludes with a summary, discussion of challenges, and potential future directions. [ABSTRACT FROM AUTHOR]

This paper introduces a deep learning method for image classification that leverages knowledge formalized as a graph created from information represented by pairs attribute/value. The proposed method investigates a loss function that adaptively combines the classical cross-entropy commonly used in deep learning with a novel penalty function. The novel loss function is derived from the representation of nodes after embedding the knowledge graph and incorporates the proximity between class and image nodes. Its formulation enables the model to focus on identifying the boundary between the most challenging classes to distinguish. Experimental results on several image databases demonstrate improved performance compared to state-of-the-art methods, including classical deep learning algorithms and recent algorithms that incorporate knowledge represented by a graph. [ABSTRACT FROM AUTHOR]

This paper proposes a new model for creating fuzzy time series and conducting future forecasts using the Bi-directional Long Short-term Memory model (Bi-LSTM). This study contributes by using both classical machine learning and deep learning techniques. Firstly, a self-updating clustering algorithm is used to determine the optimal number of clusters for time series. Secondly, the study describes a method for determining the fuzzy relationship between elements of time series and the identified clusters. Thirdly, the developed model creates the fuzzy time series based on the established rules. Finally, forecasting for the future value using the Bi-LSTM model with some improvement in optimizing the parameters and increasing the accuracy of forecasting result. The steps of the proposed model are clearly illustrated by a numerical example. Moreover, this model also tested on various datasets, including M3, M4, and M5 datasets. By evaluating its performance using parameters such as sMAPE and RMSSE, the proposed model has shown significant enhancements when compared to existing models. Additionally, the model's effectiveness is further demonstrated through its successful application in forecasting the VN index stock in Vietnam. [ABSTRACT FROM AUTHOR]

This Editorial paper provides an overview of a selection of contributions from researchers working in the fields of Subdivision, Applied Geometric and Algebraic Methods, Isogeometric Analysis, Refinability and Geometric Deep Learning, with special emphasis on numerical computation, advanced algorithms, their analysis, and their applications. [ABSTRACT FROM AUTHOR]

Deep Q-Networks algorithm (DQN) was the first reinforcement learning algorithm using deep neural network to successfully surpass human level performance in a number of Atari learning environments. However, divergent and unstable behaviour have been long standing issues in DQNs. The unstable behaviour is often characterised by overestimation in the Q -values, commonly referred to as the overestimation bias. To address the overestimation bias and the divergent behaviour, a number of heuristic extensions have been proposed. Notably, multi-step updates have been shown to drastically reduce unstable behaviour while improving agent's training performance. However, agents are often highly sensitive to the selection of the multi-step update horizon (n), and our empirical experiments show that a poorly chosen static value for n can in many cases lead to worse performance than single-step DQN. Inspired by the success of n -step DQN and the effects that multi-step updates have on overestimation bias, this paper proposes a new algorithm that we call 'Elastic Step DQN' (ES-DQN) to alleviate overestimation bias in DQNs. ES-DQN dynamically varies the step size horizon in multi-step updates based on the similarity between states visited. Our empirical evaluation shows that ES-DQN out-performs n -step with fixed n updates, Double DQN and Average DQN in several OpenAI Gym environments while at the same time alleviating the overestimation bias. [ABSTRACT FROM AUTHOR]

We present a deep learning-based method for Visible-Infrared person Re-Identification (VI-ReID). The major contribution lies in the incorporation of co-segmentation into a multi-task learning framework for VI-ReID, where the co-segmentation concept aids in making the distributions of RGB images and IR images the same for the same identity but diverse for different identities. Accordingly, a novel multi-task learning based model, i.e., co-segmentation assisted VI-ReID (CSVI), is proposed in this paper. Specifically, the co-segmentation network first takes as the inputs the modality-shared features extracted from a set of RGB and IR images by using the VI-ReID model. Then, it exploits their semantic similarities for predicting the person masks of the common identities within the input RGB and IR images by using a cross-modality center based weight generation module and a segmentation decoder. Doing so enables the VI-ReID model to extract more additional modality-shared shape features for boosting performance. Meanwhile, the co-segmentation network implicitly establishes the interactions among the set of RGB and IR images, thus further bridging the large modality discrepancies. Our model's effectiveness and superiority are verified through experimental comparisons with state-of-the-art algorithms on several benchmark datasets. • Using the co-segmentation to assist the VI-ReID in a multi-task learning framework. • Co-segmenting the same identity from a set of input images with different modalities. • Providing theoretical comparisons between our proposed model and existing models. [ABSTRACT FROM AUTHOR]

Most image inpainting algorithms have problems such as fuzzy images, texture distortion and semantic inaccuracy, and the image inpainting effect is limited when processing photos with large missing sections and resolution levels. The paper proposes an effective image inpainting algorithm via partial multi-scale channel attention mechanism and deep neural networks to address the above phenomenon that existing image inpainting methods using deep learning modules have insufficient perception and representation capabilities for multi-scale features with high proportion of irregular defects. Initially, we used the Res-U-Net module as a generator. The U-Net-like backbone network topology can achieve the encoding and decoding stages of damaged images. Secondly, the residual network structure was built in the encoder and decoder to improve the ability of the proposed network to extract and display the features of the damaged images. Finally, the partial multi-scale channel attention module was inserted in the skip connection with the decoder to increase the efficiency of using the low-level features of the original images. The experimental results of the research can show that the proposed method outperforms state-of-the-art methods in terms of subjective visual perception and objective evaluation indicators on the CelebA , Places2 and Paris Street View datasets. • The model has improved the ability to extract and express multi-scale features. • The method had included partial multi-scale channel attention and residual network. • The backbone network structure can realize encoding and decoding stage. • The structure of residual networks had constructed to enhance the abilities. [ABSTRACT FROM AUTHOR]

As the development of the Internet and IT technology, short-text based communication is so popular compared with voice based one. Chat-based communication enables rapid, short and massive exchange of message with many people, creates new social problems. 'Cross-texting' is one of them. It refers to accidentally sending a text to an unintended person during the concurrent conversations with separated multiple people. Cross-texting would be a serious problem in languages where respectful expressions are required. As text-based communication is getting popular, it is a crucial work to prevent cross-texting by detecting it in advance in languages with honorifics expression such as Korean. In this paper, we proposed two methods detecting a cross-text using a deep learning model. The first model is the formal feature vector, which models dialog by explicitly defining the politeness and completeness features. The second one is the grpah2vec based ChatGram-net model, which models the dialog based on the syllable occurrence relationship. To evaluate the detection performance, we suggest a generating method for cross-text datasets from a actual messenger corpus. In experiment we show that both proposed models detected cross-text effectively, and exceeded the performance of the baseline models. [ABSTRACT FROM AUTHOR]

Computer-generated holography (CGH) is a technique that aims to produce specific illumination patterns using coherent light. However, traditional CGH algorithms often struggle to balance computational speed with the accuracy of the generated hologram. To address this issue, a non-iterative algorithm named "DL-GSA" is proposed in this paper. DL-GSA combines unsupervised learning in machine learning with convolutional neural networks (CNN) to generate holograms with high accuracy and fixed computational complexity. Simulation experiments reveal that DL-GSA generates hologram patterns faster than the Modified Gerchberg-Saxton algorithm (MGSA) and double-phase retrieval algorithm (DPRA). Furthermore, the average accuracy of the generated holograms is higher than 95 %. These findings suggest that DL-GSA has the potential to significantly enhance the real-time hologram generation capabilities, making it a promising technique for future applications. [ABSTRACT FROM AUTHOR]

Segmentation of bowel sounds (BS) events is a significant task of automatic BS monitoring. Recently, deep learning (DL) has been utilized to realize the segmentation of BS events. However, most researchers treat BS segmentation as a traditional classification problem, which causes that more precise locations for the occurrence of BS events are unable to obtained. Besides, the performance of segmentation of BS events is easily affected by thresholds of model output in practical applications. To tackle these issues, in this paper, a lightweight DL-based BS segmentation algorithm is proposed. The one-dimensional convolution layers and bidirectional gate recurrent unit (GRU) layers are adopted to enhance the ability of feature extraction. A loss function named shape loss is proposed to reduce the sensitivity of model to thresholds. Moreover, a portable BS monitoring device is developed to realize data acquisition, display and algorithm deployment. Based on this device, experiments on human and rats are conducted to verify the effectiveness of our proposed approach. Experimental results shows that the proposed method outperforms other comparison methods with the higher f1-scores and lower sensitivity to thresholds. [ABSTRACT FROM AUTHOR]

The challenges posed by high pixel resolution and complex backgrounds in UAV remote sensing images have hindered the effective feature extraction and precise bounding box regression for small targets. In response to these challenges, numerous detection methods based on deep learning have emerged in recent years. Despite their advancements, these methods have not fully addressed the demand for accurate identification of small targets in remote sensing images. This paper introduces DSAA-YOLO, a novel algorithm designed for small target detection in UAV remote sensing images. Firstly, a new data augmentation strategy, termed Super Resolution Data Augment (SRDA), is proposed, which integrates the concept of image super-resolution to enrich the dataset while preserving data quality. Furthermore, a Dense Residual-based Super-Resolution module (DRSR) is introduced to enhance the resolution of small targets that have undergone quality degradation due to transformations. Subsequently, an Information Alignment Feature Enhancement Module (IAFE) is proposed to maximize the extraction of original features from the image. Finally, based on the improved Multi-Objective Grey Wolf Optimization (MOGWO), a novel dynamic anchor regression strategy termed Multi-Object Golf Dynamic Anchor (MGDA) is devised to generate more precise bounding boxes. The proposed DSAA-YOLO algorithm demonstrates significant improvements over current state-of-the-art methods in terms of widely recognized metrics including mAP, and AP50 on the VisDrone dataset. [ABSTRACT FROM AUTHOR]