Multiple Transformations Research Articles

EryDB: A Transcriptomic Profile Database for Erythropoiesis and Erythroid-related Diseases.

Erythropoiesis is a finely regulated and complex process that involves multiple transformations from hematopoietic stem cells to mature red blood cells at hematopoietic sites from the embryonic to the adult stages. Investigations into its molecular mechanisms have generated a wealth of expression data, including bulk and single-cell RNA sequencing data. A comprehensively integrated and well-curated erythropoiesis-specific database will greatly facilitate the mining of gene expression data and enable large-scale research of erythropoiesis and erythroid-related diseases. Here, we present EryDB, an open-access and comprehensive database dedicated to the collection, integration, analysis, and visualization of transcriptomic data for erythropoiesis and erythroid-related diseases. Currently, the database includes expertly curated quality-assured data of 3803 samples and 1,187,119 single cells derived from 107 public studies of three species (Homo sapiens, Mus musculus, and Danio rerio), nine tissue types, and five diseases. EryDB provides users with the ability to not only browse the molecular features of erythropoiesis between tissues and species, but also perform computational analyses of single-cell and bulk RNA sequencing data, thus serving as a convenient platform for customized queries and analyses. EryDB v1.0 is freely accessible at https://ngdc.cncb.ac.cn/EryDB/home.

Physics-Guided Deep Learning for Plate Permeability Estimation With Single to Multiple Frequency Transformation of Eddy-Current Testing

Physics-Guided Deep Learning for Plate Permeability Estimation With Single to Multiple Frequency Transformation of Eddy-Current Testing

Generalized Multiple Multiplicative Fourier Transform and Estimates of Integral Moduli of Continuity

Generalized Multiple Multiplicative Fourier Transform and Estimates of Integral Moduli of Continuity

A novel time-varying grey Fourier model for variable amplitude seasonal fluctuation sequences

PurposeA time-varying grey Fourier model (TVGFM(1,1,N)) is proposed for the simulation of variable amplitude seasonal fluctuation time series, as the performance of traditional grey models can't catch the time-varying trend well.Design/methodology/approachThe proposed model couples Fourier series and linear time-varying terms as the grey action, to describe the characteristics of variable amplitude and seasonality. The truncated Fourier order N is preselected from the alternative order set by Nyquist-Shannon sampling theorem and the principle of simplicity, then the optimal Fourier order is determined by hold-out method to improve the robustness of the proposed model. Initial value correction and the multiple transformation are also studied to improve the precision.FindingsThe new model has a broader applicability range as a result of the new grey action, attaining higher fitting and forecasting accuracy. The numerical experiment of a generated monthly time series indicates the proposed model can accurately fit the variable amplitude seasonal sequence, in which the mean absolute percentage error (MAPE) is only 0.01%, and the complex simulations based on Monte-Carlo method testify the validity of the proposed model. The results of monthly electricity consumption in China's primary industry, demonstrate the proposed model catches the time-varying trend and has good performances, where MAPEF and MAPET are below 5%. Moreover, the proposed TVGFM(1,1,N) model is superior to the benchmark models, grey polynomial model (GMP(1,1,N)), grey Fourier model (GFM(1,1,N)), seasonal grey model (SGM(1,1)), seasonal ARIMA model seasonal autoregressive integrated moving average model (SARIMA) and support vector regression (SVR).Originality/valueThe parameter estimates and forecasting of the new proposed TVGFM are studied, and the good fitting and forecasting accuracy of time-varying amplitude seasonal fluctuation series are testified by numerical simulations and a case study.

U-NTCA: nnUNet and nested transformer with channel attention for corneal cell segmentation.

Automatic segmentation of corneal stromal cells can assist ophthalmologists to detect abnormal morphology in confocal microscopy images, thereby assessing the virus infection or conical mutation of corneas, and avoiding irreversible pathological damage. However, the corneal stromal cells often suffer from uneven illumination and disordered vascular occlusion, resulting in inaccurate segmentation. In response to these challenges, this study proposes a novel approach: a nnUNet and nested Transformer-based network integrated with dual high-order channel attention, named U-NTCA. Unlike nnUNet, this architecture allows for the recursive transmission of crucial contextual features and direct interaction of features across layers to improve the accuracy of cell recognition in low-quality regions. The proposed methodology involves multiple steps. Firstly, three underlying features with the same channel number are sent into an attention channel named gnConv to facilitate higher-order interaction of local context. Secondly, we leverage different layers in U-Net to integrate Transformer nested with gnConv, and concatenate multiple Transformers to transmit multi-scale features in a bottom-up manner. We encode the downsampling features, corresponding upsampling features, and low-level feature information transmitted from lower layers to model potential correlations between features of varying sizes and resolutions. These multi-scale features play a pivotal role in refining the position information and morphological details of the current layer through recursive transmission. Experimental results on a clinical dataset including 136 images show that the proposed method achieves competitive performance with a Dice score of 82.72% and an AUC (Area Under Curve) of 90.92%, which are higher than the performance of nnUNet. The experimental results indicate that our model provides a cost-effective and high-precision segmentation solution for corneal stromal cells, particularly in challenging image scenarios.

A novel global calibration method for vision measurement system based on mirror-image stereo target

Using three-dimensional (3D) targets to solve the transformation relationship between the local and global coordinate systems is a common global calibration method. However, 3D targets have complex structures and high costs. And multiple coordinate transformations during global calibration can cause significant cumulative errors. Therefore, based on reflection imaging, this paper designs a new mirror-image stereo target (MST) and analyzes its view area and three structural parameter constraints. A new global calibration method is proposed, as well as three optimization algorithms for pose solution between MST, optical 3D sensor and global camera to improve the global calibration accuracy. The experimental results show that the registration errors of two workpieces are 0.086 mm and 0.114 mm, respectively, confirming the feasibility and precision of the proposed method. Our method is flexible, requiring only a planar target and a mirror, rather than complex 3D targets, to achieve global calibration with non-overlapping field of view.

Mask-Homo: Pseudo Plane Mask-Guided Unsupervised Multi-Homography Estimation

Homography estimation is a fundamental problem in computer vision. Previous works mainly focus on estimating either a single homography, or multiple homographies based on mesh grid division of the image. In practical scenarios, single homography is inadequate and often leads to a compromised result for multiple planes; while mesh grid multi-homography damages the plane distribution of the scene, and does not fully address the restriction to use homography. In this work, we propose a novel semantics guided multi-homography estimation framework, Mask-Homo, to provide an explicit solution to the multi-plane depth disparity problem. First, a pseudo plane mask generation module is designed to obtain multiple correlated regions that follow the plane distribution of the scene. Then, multiple local homography transformations, each of which aligns a correlated region precisely, are predicted and corresponding warped images are fused to obtain the final result. Furthermore, a new metric, Mask-PSNR, is proposed for more comprehensive evaluation of alignment. Extensive experiments are conducted to verify the effectiveness of the proposed method. Our code is available at https://github.com/SAITPublic/MaskHomo.

Bi-directional Adapter for Multimodal Tracking

Due to the rapid development of computer vision, single-modal (RGB) object tracking has made significant progress in recent years. Considering the limitation of single imaging sensor, multi-modal images (RGB, infrared, etc.) are introduced to compensate for this deficiency for all-weather object tracking in complex environments. However, as acquiring sufficient multi-modal tracking data is hard while the dominant modality changes with the open environment, most existing techniques fail to extract multi-modal complementary information dynamically, yielding unsatisfactory tracking performance. To handle this problem, we propose a novel multi-modal visual prompt tracking model based on a universal bi-directional adapter, cross-prompting multiple modalities mutually. Our model consists of a universal bi-directional adapter and multiple modality-specific transformer encoder branches with sharing parameters. The encoders extract features of each modality separately by using a frozen, pre-trained foundation model. We develop a simple but effective light feature adapter to transfer modality-specific information from one modality to another, performing visual feature prompt fusion in an adaptive manner. With adding fewer (0.32M) trainable parameters, our model achieves superior tracking performance in comparison with both the full fine-tuning methods and the prompt learning-based methods. Our code is available: https://github.com/SparkTempest/BAT.

Inverse Weight-Balancing for Deep Long-Tailed Learning

The performance of deep learning models often degrades rapidly when faced with imbalanced data characterized by a long-tailed distribution. Researchers have found that the fully connected layer trained by cross-entropy loss has large weight-norms for classes with many samples, but not for classes with few samples. How to address the data imbalance problem with both the encoder and the classifier seems an under-researched problem. In this paper, we propose an inverse weight-balancing (IWB) approach to guide model training and alleviate the data imbalance problem in two stages. In the first stage, an encoder and classifier (the fully connected layer) are trained using conventional cross-entropy loss. In the second stage, with a fixed encoder, the classifier is finetuned through an adaptive distribution for IWB in the decision space. Unlike existing inverse image frequency that implements a multiplicative margin adjustment transformation in the classification layer, our approach can be interpreted as an adaptive distribution alignment strategy using not only the class-wise number distribution but also the sample-wise difficulty distribution in both encoder and classifier. Experiments show that our method can greatly improve performance on imbalanced datasets such as CIFAR100-LT with different imbalance factors, ImageNet-LT, and iNaturelists2018.

Evaluation of Large Language Models on Code Obfuscation (Student Abstract)

Obfuscation intends to decrease interpretability of code and identification of code behavior. Large Language Models(LLMs) have been proposed for code synthesis and code analysis. This paper attempts to understand how well LLMs can analyse code and identify code behavior. Specifically, this paper systematically evaluates several LLMs’ capabilities to detect obfuscated code and identify behavior across a variety of obfuscation techniques with varying levels of complexity. LLMs proved to be better at detecting obfuscations that changed identifiers, even to misleading ones, compared to obfuscations involving code insertions (unused variables, as well as variables that replace constants with expressions that evaluate to those constants). Hardest to detect were obfuscations that layered multiple simple transformations. For these, only 20-40% of the LLMs’ responses were correct. Adding misleading documentation was also successful in misleading LLMs. We provide all our code to replicate results at https://github.com/SwindleA/LLMCodeObfuscation. Overall, our results suggest a gap in LLMs’ ability to understand code.

Hear You Say You: An Efficient Framework for Marine Mammal Sounds’ Classification

Marine mammals and their ecosystem face significant threats from, for example, military active sonar and marine transportation. To mitigate this harm, early detection and classification of marine mammals are essential. While recent efforts have utilized spectrogram analysis and machine learning techniques, there remain challenges in their efficiency. Therefore, we propose a novel knowledge distillation framework, named XCFSMN, for this problem. We construct a teacher model that fuses the features extracted from an X-vector extractor, a DenseNet and Cross-Covariance attended compact Feed-Forward Sequential Memory Network (cFSMN). The teacher model transfers knowledge to a simpler cFSMN model through a temperature-cooling strategy for efficient learning. Compared to multiple convolutional neural network backbones and transformers, the proposed framework achieves state-of-the-art efficiency and performance. The improved model size is approximately 20 times smaller and the inference time can be 10 times shorter without affecting the model’s accuracy.

Visible and Infrared Object Tracking Based on Multimodal Hierarchical Relationship Modeling

Visible RGB and Thermal infrared (RGBT) object tracking has emerged as a prominent area of focus within the realm of computer vision. Nevertheless, the majority of existing RGBT tracking methods, which predominantly rely on Transformers, primarily emphasize the enhancement of features extracted by convolutional neural networks. Unfortunately, the latent potential of Transformers in representation learning has been inadequately explored. Furthermore, most studies tend to overlook the significance of distinguishing between the importance of each modality in the context of multimodal tasks. In this paper, we address these two critical issues by introducing a novel RGBT tracking framework centered on multimodal hierarchical relationship modeling. Through the incorporation of multiple Transformer encoders and the deployment of self-attention mechanisms, we progressively aggregate and fuse multimodal image features at various stages of image feature learning. Throughout the process of multimodal interaction within the network, we employ a dynamic component feature fusion module at the patch-level to dynamically assess the relevance of visible information within each region of the tracking scene. Our extensive experimentation, conducted on benchmark datasets such as RGBT234, GTOT, and LasHeR, substantiates the commendable performance of our proposed approach in terms of accuracy, success rate, and tracking speed.

Asymmetric Organocatalyzed Transfer Hydroxymethylation of Isoindolinones Using Formaldehyde Surrogates.

The piperidine-based Takemoto catalyst has been successfully employed in a novel asymmetric transfer hydroxymethylation of activated isoindolinones, allowing us to prepare the enantioenriched hydroxymethylated adducts in good to excellent yields (48-96%) and enantiopurities (81:19-97:3 e.r.). To increase the reaction rate without compromising the selectivity, carefully optimized formaldehyde surrogates were employed, providing a convenient source of anhydrous formaldehyde with a base-triggered release. The substrate scope, including 34 entries, showed the considerable generality of the asymmetric transformation, and most entries exhibited complete conversions in 24-48 h. A scale-up experiment and multiple enantioselective downstream transformations were also carried out, suggesting the prospective synthetic utility of the products.

Good architectural design as a catalyst for improving the quality of life in cities

The growth of cities has led to multiple transformations that have changed the urban fabric; for this reason, many locations in urban areas remain neglected. The present study was undertaken to search for solutions that would minimize adverse changes in the urban fabric, buildings, and urban spaces. The aim of the study was to present examples of good architectural design that can be considered catalysts that improve the quality of life in cities. Architectural design contributes to urban development not only at the level of individual buildings, but also at the level of the overall quality of urban life. The research methodology involved developing a theoretical framework for the research topic, and applying selected indicators to analyse several international examples and investigate the strategies deployed in various countries around the world. The study demonstrated that good architectural design must be inspired by a city’s history, and that the urban context should be considered in order to integrate new urban development with the surrounding environment through catalytic mechanisms and their indicators. Sustainability, health, education, safety, psychology, material sourcing, and building materials are the most important quality of life (QoL) factors for developing a good architectural project.

Cascade transformers with dynamic attention for video question answering

Visual question answering (VQA) has become a hot study topic with challenging motivation of correctly answering the videos or images questions in recent years. However, the existing VQA model mostly aimed at answering questions about images and performed poorly in the video question answering (VideoQA) domain. VideoQA needs to simultaneously consider the correlations between video frames and the dynamic information of multiple objects in video. Therefore, we propose a novel Cascade Transformers with Dynamic Attention for Video Question Answering (CTDA-QA), which aims to simultaneously solve the above considerations. Specifically, the proposed CTDA-QA model utilizes multiple transformers structure to encode videos for reasoning complex spatial and temporal information, which is different from the previous recurrent neural network methods. Besides, in order to effectively capture the dynamic information from various scenarios in videos, a flexible attention module has been proposed to explore the essential relations between objects in a dynamic timeline. Finally, to avoid spurious answers and fully explore the cross-modal relationships, a mixed-supervised learning strategy is designed for optimizing the reasoning tasks. The experiments on several benchmark video question–answer datasets clearly verify the performance and effectiveness of CTDA-QA, which contains the results in contrast to the state-of-the-art methods. Besides, the provided ablation study and visualization results further reveal the potential of CTDA-QA.

PHYTOCHEMICAL PROFILING of VOLATILE COMPONENTS of Echinacea purpurea (L.) MOENCH MULTIPLIED by MICROPROPAGATION TECHNIQUE

Echinacea purpurea (L.) Moench is a substantial herbaceous perennial species of ornamental and medicinal flowering plant that grows to 120 cm in maturity from the Asteraceae family and the Echinacea genus. The development of in vitro protocols for this plant can have a significant impact on the global deployment of this beneficial germplasm. It will also facilitate the rapid multiplication, biotransformation, and genetic transformation of improved phytochemical production, particularly secondary metabolites. All stages of E. purpurea micropropagation in vitro and acclimatization to in vivo conditions were investigated in this study. Furthermore, the obtained volatile components of the plants were determined in this study. The research findings revealed that the best seed sterilization was observed with 15% commercial bleach for 5 minutes. MS plant tissue culture medium including 1.25 mg L-1 6-benzyl amino purine was suitable for regeneration and the high shoot regeneration was %75 and MS medium containing 1.00 mg L-1 indole 3 butyric acid was appropriate for rooting. Furthermore, the findings show that peat is an appropriate substance for acclimation of rooted plantlets. Germacrene D, caryophyllene, Borneol, Caryophyllene oxide, and Myrtenal were identified as the main volatile components of E. purpurea by GC/MS and GC/FID analysis.

Large Cyclability of Elastocaloric Effect in Highly Porous Ni-Fe-Ga Foams.

Solid-state refrigeration based on elastocaloric materials (eCMs) requires reversibility and repeatability. However, the intrinsic intergranular brittleness of ferromagnetic shape memory alloys (FMSMAs) limits fatigue life and, thus, is the crucial bottleneck for its industrial applications. Significant cyclic stability of elastocaloric effects (eCE) via 53% porosity in Ni-Fe-Ga FMSMA has already been proven. Here, Ni-Fe-Ga foams (single-/hierarchical pores) with high porosity of 64% and 73% via tailoring the material's architecture to optimize the eCE performances are studied. A completely reversible superelastic behavior at room temperature (297 K) is demonstrated in high porosity (64-73%) Ni-Fe-Ga foams with small stress hysteresis, which is greatly conducive to durable fatigue life. Consequentially, hierarchical pore foam with 64% porosity exhibits a maximum reversible ∆Tad of 2.0 K at much lower stress of 45 MPa with a large COPmat of 34. Moreover, it shows stable elastocaloric behavior (ΔTad = 2.0 K) over >300 superelastic cycles with no significant deterioration. The enhanced eCE cyclability can be attributed to the pore hierarchies, which remarkably reduce the grain boundary constraints and/or limit the propagation of cracks to induce multiple stress-induced martensitic transformations (MTs). Therefore, this work paves the way for designing durable fatigue life FMSMAs as promising eCMs by manipulating the material architectures.

A synthesis method for epicyclic chains based on new topological model and similarity

The structural design is a prerequisite for the creation of mechanical equipment. This study focuses on the structural synthesis of epicyclic chains (ECs), and proposes a new topological model and synthesis method of ECs to address the existing research problems (i.e. synthesis dependence on multiple graphic transformations and the generation of pseudo-isomorphism). First, the structural characteristics of ECs are analyzed to explore the relation between their axles, gears, and planet carriers, and the corresponding topological model and the adjacency matrix expression of ECs are provided. Then, the topological elements corresponding to the axles, gears, and gear pairs are added sequentially to the topological graph corresponding to the planet carriers, and the constraints are established based on similarity to inhibit the generation of isomorphism. Finally, all the databases of feasible ECs are obtained through gear loop discrimination. All processes are carried out with computer assistance. The synthesis results of the ECs with 1–3 degrees of freedom and up to 10 components are presented. The logic of this paper is to simplify (or optimize) the synthesis process to improve efficiency of structural synthesis, which will break through the threshold of computing power and provide more possibilities for the design of mechanical equipment.

DMFF: Deep multimodel feature fusion for building occupancy detection

The 2022 Global Status Report for Buildings and Construction (Buildings-GSR) indicates that construction activities have returned to pre-pandemic levels in most major economies, alongside more building energy consumption. To achieve the Net Zero emissions target by 2050, particularly in the post-pandemic era, accurate occupancy information is important to enhance building energy efficiency and improve occupancy comfort. While remarkable progress has been made in existing studies, they struggle to make full use of multi-sensor data to achieve high accuracy. Furthermore, there is a high expectation of the multimodel multi-temporary fusion by Transformer. In this study, we present a Transformer-based multimodal, multi-temporal feature fusion method (DMFF) for occupancy detection. To transfer domain knowledge from artificial intelligence into the building area, DMFF includes a pretrain-finetune pipeline and leverages pre-trained visual and sound models. Multiple pre-trained Transformer encoders are employed to extract features of different modalities. Then, we propose a self-attention mechanism for modality fusion to learn relationships among various sensors. Our DMFF method demonstrates superior performance on a real dataset, outperforming machine and deep learning methods (e.g., Convolutional Neural Networks, Random Forest, and Multilayer Perceptrons). Applied to a room setting, DMFF shows promising potential for building energy savings. The code and demo are accessible at https://github.com/kailaisun/multimodel_occupancy.

The Temporal and Spatial Characteristics of Wind–Photovoltaic–Hydro Hybrid Power Output Based on a Cloud Model and Copula Function

In a high proportion of wind–photovoltaic–hydro hybrid power systems, fluctuation and dispersion make it difficult to accurately quantify the output characteristics. Therefore, in this study, a cloud model and copula correlation coefficient matrix were constructed for a hybrid power generation system based on the output data. Multiple backward cloud transformation based on the sampling-with-replacement method was proposed to calculate the improved entropy and hyperentropy to analyze the fluctuation range and dispersion degree quantitatively. A similarity index was proposed to evaluate the similarity between wind power, PV power, and hydropower. A suitable copula function was selected, and the Kendall and Spearman coefficients show the correlation relationships of the hybrid systems. The temporal and spatial characteristics of the hybrid systems were analyzed based on the two models. A typical example in Qinghai proved the effectiveness and applicability of the method. The results show that the correlation between photovoltaic power and hydropower is better and that, in summer, hydropower can be used to adjust the output of renewable energy.