Feedback Network Research Articles

Transmit Precoding via Block Diagonalization with Approximately Optimized Distance Measures for Limited Feedback in Dense Cellular Networks with Multiantenna Base Stations

Transmit Precoding via Block Diagonalization with Approximately Optimized Distance Measures for Limited Feedback in Dense Cellular Networks with Multiantenna Base Stations

A Weighted AIMD Congestion Control Algorithm for Device-to-Device Communication in 5G Network

ABSTRACT Device-to-Device (D2D) communication offers promising benefits in 5G networks in terms of improved throughput and reduced latency. However, efficient congestion control remains a critical challenge to ensure optimal performance and resource utilization. Existing congestion control mechanisms often struggle with adapting to dynamic network conditions, leading to inefficiencies, such as underutilization of network resources or excessive packet loss. This paper addresses these challenges by proposing a novel Weighted AIMD congestion control algorithm tailored specifically for D2D communication in 5G networks (WACC-D2DC-5GN). Here, the Weighted AIMD Congestion Control Algorithm is proposed for estimating available bandwidth and Hunger Games Search Optimization to optimize the weight parameter of WACC. The proposed algorithm integrates weighted factors that dynamically adjust congestion window sizes based on real-time network feedback. Simulations are run on the NS3-mmWave module, NS3 LTE-A module. The simulation outcomes show that the proposed WACC-D2DC-5GN method attains 27.26%, 20.41%, and 23.26% higher SNR and 16.20%, 26.97%, and 30.34% higher Throughput when analysed with existing techniques like NexGen D-TCP: next generation dynamic TCP congestion control approach (NGD-TCP-CCA), user-centric channel allocation system for 5G higher-speed users by using ML to decrease handover rate (UCC-HSU-MLA), and efficient with reliable hybrid deep learning-allowed method for congestion control in 5G/6G networks (HDL-EMC-CN) respectively.

Towards fine-grained adaptive video captioning via Quality-Aware Recurrent Feedback Network

To achieve accurate video captioning, most existing solutions focus on employing auxiliary features to provide complementary generation clues, such as detected target regions, audio speech signals, and in-plane text. However, beyond introducing external information, the potential of using the generated captions has been overlooked. We argue that the intrinsic value lies in the caption text, which can faithfully reflect the video content. To this end, we propose to reuse the captions via a Quality-Aware Recurrent Feedback Network (QARFNet), a model that progressively exploits the supportive power between video features and the generated captions. Specifically, inspired by the backtracking AdaBoost algorithm, we propose to build a recurrent loop structure that recycles the obtained linguistic predictions to refine the input visual features. Referring to the greedy selective nature of the AdaBoost algorithm, we set a quality-aware gate to assess the necessity of forwarding the next loop, lessening the complexity. After the refinement loop, if the confidence score remains below the predefined threshold, we select the output with the highest confidence score to advance the subsequent transformer decoder. To facilitate feedback in each loop, a Multi-level Update Module is constructed before fusing linguistic predictions with video features. This involves extracting nouns and verbs from linguistic predictions to lighten relevant video tokens, achieving self-interactions across recurrent loops. By merging the coarse-grained and gradually refined linguistic prediction features, the video tokens are semantically closer to the desired textual representation. To alleviate the increased calculation caused by the loops, we employ a flat transformer encoder to decrease the complexity. The experimental results on several benchmark datasets confirm the effectiveness of our approach, with superior performance compared to the state-of-the-art.

SCANet: A lightweight deep learning network for massive MIMO CSI feedback based on spatial and channel attention mechanism

Multi-user massive multiple-input multiple-output (MIMO) communication systems consume too much downlink bandwidth due to the huge channel state information (CSI) feedback, deep learning-based CSI feedback approaches fortunately can alleviate the feedback overhead while obtaining an accurate CSI. However, there is a trade-off between the high feedback performance and low computational complexity. In this paper, a low-complexity CSI feedback approach is proposed based on spatial and channel attention mechanism, namely the Spatial and Channel Attention Network (SCANet). Specifically, the spatial and channel attention mechanism makes the network’s attention mainly focus on the specific spatial regions and key feature channels. We devise a serial architecture in the encoder that composes of Spatial and Channel Attention Block (SCAB) and Encoder Transformer Block. Moreover, we design a hybrid architecture in the decoder that composes of the CNNs Block and Decoder Transformer Block. These designs enable the network to effectively extract both global and local CSI features. Computer simulations in both the indoor and outdoor scenarios show that under the same system configurations, the proposed low-complexity SCANet achieves almost the same performance as the state-of-the-art network while reducing the computational complexity by 85.76% fewer floating-point operations per second (FLOPS) on average.

Quantitative modeling of signaling in aggressive B cell lymphoma unveils conserved core network.

B cell receptor (BCR) signaling is required for the survival and maturation of B cells and is deregulated in B cell lymphomas. While proximal BCR signaling is well studied, little is known about the crosstalk of downstream effector pathways, and a comprehensive quantitative network analysis of BCR signaling is missing. Here, we semi-quantitatively modelled BCR signaling in Burkitt lymphoma (BL) cells using systematically perturbed phosphorylation data of BL-2 and BL-41 cells. The models unveiled feedback and crosstalk structures in the BCR signaling network, including a negative crosstalk from p38 to MEK/ERK. The relevance of the crosstalk was verified for BCR and CD40 signaling in different BL cells and confirmed by global phosphoproteomics on ERK itself and known ERK target sites. Compared to the starting network, the trained network for BL-2 cells was better transferable to BL-41 cells. Moreover, the BL-2 network was also suited to model BCR signaling in Diffuse large B cell lymphoma cells lines with aberrant BCR signaling (HBL-1, OCI-LY3), indicating that BCR aberration does not cause a major downstream rewiring.

Capturing the context of drug use for college students: A Contextual Behavioural Science informed qualitative Analysis of Harm reduction practices using network feedback loops simulation modelling

Drug use during college can have substantial harm on students’ lives and impacts the institutions’ functioning and local communities. Yet existing interventions for drug use at college poorly address the concurrent dynamic influences of the experiences in earlier developmental periods of young adults and the proximal contextual triggers of college life; both risk factors that contribute to drug use. In answer to this, system dynamic methods and contextual-behavioural science (CBS) approaches can support the development of interventions to address these risk factors. Using Causal Loop Diagram methods (Vensim PLE), we collected qualitative data from college students (n=24, aged 22 years old), during the development phase of MyUse: a contextual behavioural change intervention for harm reduction practices at college students, to generate Network Feedback Loops (NFLs). The findings underscore central nodes (determinants within an intervention) that can support our previous identified three CBS-harm-reduction practices for college students (targeted edges: mindful drug-use decision making, value-based activities, context-sensitive personalized plan of harm reduction). Analyses revealed 4 NFLs for students with previous drug use, consisting of 13 edges (4 positive, 2 negative, and 4 balancing reinforcing relationships) and 3 NFLs for students with no previous drug use, consisting of 4 positives, one negative, and one balancing relationship. All these determinants (manipulable variables) are nested with the three CBS-related targeted outcomes. College students who use drugs need drug-related knowledge about the unpredictable and adverse effects of drugs, presented in a compassionate way and distributed from credible resources (e.g., students’ unions/ club). Students with no previous drug use need education about the effects of drugs and awareness of how drugs can devaluate value-based activities (e.g. sports, friendships, social life). These should be delivered via proxy cue reminders and mobile-text-messages conveying drug use susceptibility, distributed in real-time. Idiosyncratic, dynamic, and contextual-bound factors of lapse risks or preventive practices should account for each person-specific vulnerabilities via personalized harm reduction plans.

YOLOv5_mamba: unmanned aerial vehicle object detection based on bidirectional dense feedback network and adaptive gate feature fusion

Addressing the problem that the object size in Unmanned Aerial Vehicles (UAVs) aerial images is too small and contains limited feature information, leading to existing detection algorithms having less than ideal performance in small object detection, we propose a UAV aerial object detection system named YOLv5_mamba based on bidirectional dense feedback network and adaptive gate feature fusion. This paper improves the You Only Look Once Version 5 (YOLOv5) algorithm by firstly introducing the Faster Implementation of CSP Bottleneck with 2 convolutions (C2f) module from YOLOv8 into the backbone network to enhance the feature extraction capability of the backbone network. Furthermore, the mamba module and C2f module are introduced to construct a bidirectional dense feedback network to enhance the transfer of contextual information in the neck part. Thirdly, an adaptive gate feature fusion network is proposed to improve the head part of YOLOv5 and enhance its final detection capability. Experimental results on the public UAV aerial dataset VisDrone2019 demonstrate that the proposed algorithm improves the detection accuracy by 9.3% compared to the original YOLOv5 baseline network, showing better detection performance for small objects. For the UCAS_AOD dataset, the proposed algorithm outperforms YOLOv5-s by 9%. In the case of the DIOR dataset, the proposed algorithm exceeds YOLOv5-s by 12%.

Mathematical discussion in classrooms as a technologically-supported activity fostering participation and inclusion

AbstractWhole-class mathematical discussion in a problem-solving activity is recognized as a powerful pedagogical activity but also a challenge for teachers who must consider several difficulties that learners might face, particularly in terms of an overload of Working Memory and Executive Functions. This study investigates how the use of a digital platform (Padlet) can support participatory and inclusive mathematical classroom discussion. We proposed a teaching experiment based on graphical tasks anticipating integral calculus to grade 13 students, and we examined how the use of the digital platform plays a role in the construction and interpretation of new mathematical objects emerging from the activity. The use of Instrumental Genesis and Double Instrumental Genesis frameworks allowed us to make the affordances of the tool emerge. As a result, we got evidence of how mathematical discussion may develop as a network of interactions, feedback, and connection of input and discuss examples of how active participation and inclusion are enhanced by the tool affordances. Indeed, the digital platform allowed easy interaction, with many ways to represent and express the ongoing evolution of personal and shared meanings and the possibility to manage the time of the activity. This fostered students’ participation and students which did not participate in previous discussions were actively engaged in it.

The gut microbiota-immune-brain axis in a wild vertebrate: dynamic interactions and health impacts.

The gut microbiota-immune-brain axis is a feedback network which influences diverse physiological processes and plays a pivotal role in overall health and wellbeing. Although research in humans and laboratory mice has shed light into the associations and mechanisms governing this communication network, evidence of such interactions in wild, especially in young animals, is lacking. We therefore investigated these interactions during early development in a population of common buzzards (Buteo buteo) and their effects on individual condition. In a longitudinal study, we used a multi-marker approach to establish potential links between the bacterial and eukaryotic gut microbiota, a panel of immune assays and feather corticosterone measurements as a proxy for long-term stress. Using Bayesian structural equation modeling, we found no support for feedback between gut microbial diversity and immune or stress parameters. However, we did find strong relationships in the feedback network. Immunity was negatively correlated with corticosterone levels, and microbial diversity was positively associated with nestling body condition. Furthermore, corticosterone levels and eukaryotic microbiota diversity decreased with age while immune activity increased. The absence of conclusive support for the microbiota-immune-brain axis in common buzzard nestlings, coupled with the evidence for stress mediated immunosuppression, suggests a dominating role of stress-dominated maturation of the immune system during early development. Confounding factors inherent to wild systems and developing animals might override associations known from adult laboratory model subjects. The positive association between microbial diversity and body condition indicates the potential health benefits of possessing a diverse and stable microbiota.

Co-Creating an Inclusion, Diversity, Equity, and Accessibility Strategy: Defining approach and outcomes in a health data research network

BackgroundHealth Data Research Network Canada (HDRN) has committed to strengthening data use to improve health equity. Key this priority is has been an increased operationalization of Inclusion, Diversity, Equity, and Accessibility (IDEA) across the organization and within the data research processes HDRN Canada supports. Missing, however, was a unifying strategy for embedding IDEA within all HDRN Canada initiatives. ApproachGuided by results from an internal environmental scan and network feedback, HDRN Canada began developing an IDEA strategy in 2023. With the end goal of embedding IDEA across all internal teams and across all HDRN Canada strategic goals, collaborative participation methods were chosen to involve all levels of the organization. A process was designed that included focus groups, interviews, and roundtables. ResultsCo-creating the IDEA strategy required broad buy-in including detailing expectations of the planning process in advance. A flexible management approach that enabled the team to adhere to the defined process allowed the Project Team to manage unanticipated challenges. 4 key strategies emerged focusing on learning, data quality and research, leadership, and community engagement. Developing the strategy with co-creative methods helped to identify practical approaches for HDRN to prioritize IDEA within its complex data research initiatives. ConclusionHDRN Canada has outlined its commitment to IDEA in the health data ecosystem. The co-created strategy supports efforts towards accomplishing its organizational objectives and priorities. It is also a valuable resource for those in the health data space working to ensure data research contributes to equitable health outcomes.

Causal feedback loops modify lake chlorophyll a–nutrient relationships over two decades of nutrient reductions and climate warming

AbstractUnderstanding how the causal feedback between phytoplankton and environmental drivers controlling the chlorophyll a (Chl a, as a proxy of phytoplankton biomass)–nutrient relationships are modulated under different ecosystem conditions is a major challenge in aquatic ecology. Using an empirical dynamic model (convergent cross mapping) on a 20‐yr dataset on 20 Danish lakes, we quantified hypothesized causal feedback networks for each lake and related them to lake system properties (e.g., mean water depth, nutrient concentrations and extent of reduction, climate warming) vs. the Chl a–nutrient relationship (estimated from generalized least square models). The results showed prevalent causal feedback across the studied lakes, which demonstrated clear patterns for the tested ecosystem variations. Weaker causal feedbacks were found in deeper lakes and lakes with larger warming trends, while stronger causal feedbacks appeared in lakes experiencing greater reductions of TP (total phosphorus) and TN (total nitrogen). Moreover, these causal feedbacks showed a strong and positive coupled pattern. Most of the causal feedbacks worked as enhancement loops, which promote the sensitivity of phytoplankton to TP, not least in shallow lakes with a high TP reduction, and as regulatory loops, which force a shift in the Chl a–TN relationship from a more negative slope in lakes experiencing a high nutrient reduction and weak warming to a positive slope in lakes with low nutrient reduction and stronger warming. Our findings suggest a mechanistic explanation of how internal feedbacks regulate the Chl a–nutrient relationships across a broad gradient of nutrient reductions, climate warming, and lake morphologies.

Teacher Reflection on their Agency for Change (TRAC) - A tool for school-based social network learning

This short paper introduces an on-line log for Teachers’ Reflection on their Agency for Change (TRAC) designed to collect data and provide automatic visual feedback on teachers’ social networks. The TRAC tool was developed within a research project 'Making SENse of Teacher Agency for Change with Social and Epistemic Network Analysis'. The project aimed to understand how teachers exercise a form of relational agency defined as a capacity to work purposefully with others within and beyond schools, to support all learners, especially those at risk of exclusion, underachievement or other forms of marginalisation. Teachers’ reaching out to others and mobilising their social networks is an essential part of such agency. The study used Social and Epistemic Network Analysis to examine simultaneously the structural properties of teachers' social networks and the nature of content that flows through them. It also provided network visualisations and feedback to facilitate teachers’ professional reflection on how they use their relational agency to build inclusive school communities. The aim was to support teachers’ professional development by raising awareness about their individual and school network properties and nature of interactions within these networks. Part of the project was the development of the TRAC software that enabled teachers who engaged with a web-based reflective log to receive automatic feedback on their individual networks, as well as on thematic school networks, which were presented by the researchers in school development sessions. Network awareness – one’s knowledge of the resources embedded in their social ties – empowers teachers to improve the social environments of their schools. Provided alongside with the summary of research-based features of social network properties (degrees, diversity and intensity of ties), network feedback was used to facilitate professional and school development towards building inclusive communities. During the project, the TRAC tool was tested in partnerships with teachers and other staff in two schools in Stockholm. The project also had a knowledge exchange component to support relational and collaborative learning resulting from engagement with the network feedback. Network feedback based on the data from these sites was used to make adjustments to the prototype feedback tool. This short paper discusses the implications for future uses with a view towards rolling out research-informed professional reflection to larger numbers of schools and teachers anywhere, through dissemination in network learning community.

Modelling co-evolution of resource feedback and social network dynamics in human-environmental systems

Games with environmental feedback have become a crucial area of study across various scientific domains, modelling the dynamic interplay between human decisions and environmental changes, and highlighting the consequences of our choices on natural resources and biodiversity. In this work, we propose a co-evolutionary model for human-environment systems that incorporates the effects of knowledge feedback and social interaction on the sustainability of common pool resources (CPRs). The model represents consumers as agents who adjust their resource extraction based on the resource’s state. These agents are connected through social networks, where links symbolize either affinity or aversion among them. The interplay between social dynamics and resource dynamics is explored, with the system’s evolution analyzed across various network topologies and initial conditions. We find that knowledge feedback can independently sustain CPRs. However, the impact of social interactions on sustainability is dual-faceted: it can either support or impede sustainability, influenced by the network’s connectivity and heterogeneity. A notable finding is the identification of a critical network mean degree, beyond which a depletion/repletion transition parallels an absorbing/active state transition in social dynamics, i.e. individual agents and their connections are/are not prone to being frozen in their social states. Furthermore, the study examines the evolution of the social network, revealing the emergence of two polarized groups where agents within each community have the same affinity. Finally, we observe an inverse relationship between system complexity and sustainability. Comparative analyses using Monte–Carlo simulations and rate equations are employed, along with analytical arguments, to reinforce the study’s findings. The model successfully captures key aspects of the human-environment system, offering valuable insights to understand how both the spread of information and social dynamics may impact the sustainability of CPRs.

Lightning Current Measurement Method Using Rogowski Coil Based on Integral Circuit with Low-Frequency Attenuation Feedback.

A lightning current measurement method using a Rogowski coil based on an integral circuit with low-frequency attenuation feedback was proposed to address the issue of low-frequency distortion in the measurement of lightning currents on transmission lines using Rogowski coils. Firstly, the causes of low-frequency distortion in lightning current measurements using Rogowski coils were analyzed from the perspective of frequency domains. On this basis, an integration correction optimization circuit with a low-frequency attenuation feedback network was designed to correct the low-frequency distortion. The optimized integration circuit can also reduce the impact of low-frequency noise and the DC bias of the operational amplifier (op-amp) on the integration circuit due to the high low-frequency gain. Additionally, a high-pass filtering and voltage-divided sampling circuit has been added to ensure the normal operation of the integrator and improve the measurement range of the measurement system. Then, according to the relationship between the amplitude-frequency characteristics of the measurement system and the parameters of each component, the appropriate types of components and op-amp were selected to expand the measurement bandwidth. Finally, a simulation verification was conducted, and the simulation results show that this measurement method can effectively expand the lower measurement frequency limit to 20 Hz, correct the low-frequency distortion caused by Rogowski coils measuring lightning currents on transmission lines, and accurately restore the measured lightning current waveform.

COMPRESSIVE STRENGTH PREDICTION FOR SELF-COMPACTING CONCRETE USING ARTIFICIAL NEURAL NETWORKS

This study investigates the relationship between concrete constituent materials, slump values, density, strain and compressive strength. The database was set in the laboratory by performing a quality assurance test on the constituent materials to ascertain their suitability for concrete work. For material procurement and selection, the British Standard Department of Environment DOE technique of concrete trial mix designs was used. In this study, twelve concrete mixes were utilized. Two simplified models were developed using the feedback network Artificial Neural Networks architecture (ANNs) with R version 4.0.5 and R studio version 1.2.5033. In the two models, an independent layer comprising six nodes and a dependent layer comprising two nodes were taken. Having carried out the sensitivity analysis, the capacity of the developed equation was evaluated in terms of error metrics MSE and RMSE. The grading envelope for river sand showed that the graph fell perfectly into grading envelope zone 2 while other constituent materials tested were all confirmed suitable for concrete works. The results of compressive strength were obtained from varied water-cement ratios used for the concrete trial mix design which ranges between 0.45 to 0.6. The compressive strength results showed that the results increased consistently for each design mix. It is worthy of note that the strength of the mix fell between grades 15, 20, 25 and 35 respectively for both the 7-day and 28-day strength accordingly. Conversely, the ANN models predicted both 7-day and 28-day strength close to the laboratory value. It is concluded that this research has demonstrated economic viability which would enhance overall construction planning efficiency for future researchers, consultants and contractors in the building industries.

Closing the Loops on Southern Ocean Dynamics: From the Circumpolar Current to Ice Shelves and From Bottom Mixing to Surface Waves

AbstractA holistic review is given of the Southern Ocean dynamic system, in the context of the crucial role it plays in the global climate and the profound changes it is experiencing. The review focuses on connections between different components of the Southern Ocean dynamic system, drawing together contemporary perspectives from different research communities, with the objective of closing loops in our understanding of the complex network of feedbacks in the overall system. The review is targeted at researchers in Southern Ocean physical science with the ambition of broadening their knowledge beyond their specific field, and aims at facilitating better‐informed interdisciplinary collaborations. For the purposes of this review, the Southern Ocean dynamic system is divided into four main components: large‐scale circulation; cryosphere; turbulence; and gravity waves. Overviews are given of the key dynamical phenomena for each component, before describing the linkages between the components. The reviews are complemented by an overview of observed Southern Ocean trends and future climate projections. Priority research areas are identified to close remaining loops in our understanding of the Southern Ocean system.

Dual-stage feedback network for lightweight color image compression artifact reduction

Lossy image coding techniques usually result in various undesirable compression artifacts. Recently, deep convolutional neural networks have seen encouraging advances in compression artifact reduction. However, most of them focus on the restoration of the luma channel without considering the chroma components. Besides, most deep convolutional neural networks are hard to deploy in practical applications because of their high model complexity. In this article, we propose a dual-stage feedback network (DSFN) for lightweight color image compression artifact reduction. Specifically, we propose a novel curriculum learning strategy to drive a DSFN to reduce color image compression artifacts in a luma-to-RGB manner. In the first stage, the DSFN is dedicated to reconstructing the luma channel, whose high-level features containing rich structural information are then rerouted to the second stage by a feedback connection to guide the RGB image restoration. Furthermore, we present a novel enhanced feedback block for efficient high-level feature extraction, in which an adaptive iterative self-refinement module is carefully designed to refine the low-level features progressively, and an enhanced separable convolution is advanced to exploit multiscale image information fully. Extensive experiments show the notable advantage of our DSFN over several state-of-the-art methods in both quantitative indices and visual effects with lower model complexity.

BFT‐Net: A transformer‐based boundary feedback network for kidney tumour segmentation

AbstractKidney tumours are among the top ten most common tumours, the automatic segmentation of medical images can help locate tumour locations. However, the segmentation of kidney tumour images still faces several challenges: firstly, there is a lack of renal tumour endoscopic datasets and no segmentation techniques for renal tumour endoscopic images; secondly, the intra‐class inconsistency of tumours caused by variations in size, location, and shape of renal tumours; thirdly, difficulty in semantic fusion during decoding; and finally, the issue of boundary blurring in the localization of lesions. To address the aforementioned issues, a new dataset called Re‐TMRS is proposed, and for this dataset, the transformer‐based boundary feedback network for kidney tumour segmentation (BFT‐Net) is proposed. This network incorporates an adaptive context extract module (ACE) to emphasize local contextual information, reduces the semantic gap through the mixed feature capture module (MFC), and ultimately improves boundary extraction capability through end‐to‐end optimization learning in the boundary assist module (BA). Through numerous experiments, it is demonstrated that the proposed model exhibits excellent segmentation ability and generalization performance. The mDice and mIoU on the Re‐TMRS dataset reach 91.1% and 91.8%, respectively.

Arsenic activated GLUT1-mTORC1/HIF-1α-PKM2 positive feedback networks promote proliferation and migration of bladder epithelial cells

Arsenic (As) is recognized as a potent environmental contaminant associated with bladder carcinogenesis. However, its molecular mechanism remains unclear. Metabolic reprogramming is one of the hallmarks of cancer and is as a central feature of malignancy. Here, we performed the study of cross-talk between the mammalian target of rapamycin complex 1 (mTORC1)/ Hypoxia-inducible factor 1 alpha (HIF-1α) pathway and aerobic glycolysis in promoting the proliferation and migration of bladder epithelial cells treated by arsenic in vivo and in vitro. We demonstrated that arsenite promoted N-methyl-N-nitrosourea (MNU)-induced tumor formation in the bladder of rats and the malignant behavior of human ureteral epithelial (SV-HUC-1) cell. We found that arsenite positively regulated the mTORC1/HIF-1α pathway through glucose transporter protein 1 (GLUT1), which involved in the malignant progression of bladder epithelial cells relying on glycolysis. In addition, pyruvate kinase M2 (PKM2) increased by arsenite reduced the protein expressions of succinate dehydrogenase (SDH) and fumarate hydratase (FH), leading to the accumulation of tumor metabolites of succinate and fumarate. Moreover, heat shock protein (HSP)90, functioning as a chaperone protein, stabilized PKM2 and thereby regulated the proliferation and aerobic glycolysis in arsenite treated SV-HUC-1 cells. Taken together, these results provide new insights into mTORC1/HIF-1α and PKM2 networks as critical molecular targets that contribute to the arsenic-induced malignant progression of bladder epithelial cells.

DRSwin-ST: An intelligent fault diagnosis framework based on dynamic threshold noise reduction and sparse transformer with Shifted Windows

In real industrial environments, acquiring vibration data from bearings is often challenging due to noise, resulting in network models that excel when trained on datasets with sufficient samples but struggle with accurate fault identification in real-world scenarios, inevitably threatening the reliability of fault diagnosis. To address this problem, this paper proposes an end-to-end fault diagnosis framework (DRSwin-ST) based on sparse transformer with a shift window and dynamic threshold noise reduction. The Swin-Transformer serves as the backbone, leveraging a multi-head self-attention mechanism with a shift window to capture global information. The 1.5-Entmax replaces Softmax in the self-attention mechanism, sparsifying irrelevant information and allowing the model to focus on essential details. The self-attention mechanism, combined with a multi-scale structure, forms a forward feedback network to obtain rich fault feature information. In addition, the paper integrates a large convolutional kernel and a dynamic soft-threshold noise reduction module to construct a convolutional network in front of the transformer structure. This configuration extracts fault feature information and removes the noise, enhancing the fault recognition accuracy of the model. Experimental results on three diverse datasets demonstrate that DRSwin-ST exhibits robustness and high accuracy even in scenarios with limited samples and high noise, validating its exceptional performance.