Coordination Networks Research Articles

From Spectators to Participants: Rhetorical Approaches to Digital Nonviolent Resistance in Social Media Video

ABSTRACT This article contributes a rhetorical approach to nonviolent resistance that is enacted in short-form social media video environments. By examining how three viral videos on the platform TikTok reimagine the nonviolent resistance tactics of sabotage, disruption, and civil disobedience, this article considers the similarities, differences, aptitudes, and constraints of digital nonviolent resistance in social media video compared to fully offline counterparts. Consideration of three short-form social media videos that involve sabotaging an antiabortion group’s web portal, disrupting a Donald Trump campaign rally, and enacting civil disobedience by dancing without a headscarf in Iran showcase digital nonviolent resistance in social media video to more rapidly coordinate ad-hoc social networks, be more intensely calibrated for mediation, be more global and lighthearted, and be comparatively limited in scale, scope, efficacy, and risk to participants while still rhetorically generating meaningful consequences.

Coupling coordination and spatial network characteristics of carbon emission efficiency and urban green innovation in the Yellow River Basin, China

Coupling coordination and spatial network characteristics of carbon emission efficiency and urban green innovation in the Yellow River Basin, China

Balanced regulation of ROS production and inflammasome activation in preventing early development of colorectal cancer.

Reactive oxygen species (ROS) production and inflammasome activation are the key components of the innate immune response to microbial infection and sterile insults. ROS are at the intersection of inflammation and immunity during cancer development. Balanced regulation of ROS production and inflammasome activation serves as the central hub of innate immunity, determining whether a cell will survive or undergo cell death. However, the mechanisms underlying this balanced regulation remain unclear. Mitochondria and NADPH oxidases are the two major sources of ROS production. Recently, NCF4, a component of the NADPH oxidase complex that primarily contributes to ROS generation in phagocytes, was reported to balance ROS production and inflammasome activation in macrophages. The phosphorylation and puncta distribution of NCF4 shifts from the membrane-bound NADPH complex to the perinuclear region, promoting ASC speck formation and inflammasome activation, which triggers downstream IL-18-IFN-γ signaling to prevent the progression of colorectal cancer (CRC). Here, we review ROS signaling and inflammasome activation studies in colitis-associated CRC and propose that NCF4 acts as a ROS sensor that balances ROS production and inflammasome activation. In addition, NCF4 is a susceptibility gene for Crohn's disease (CD) and CRC. We discuss the evidence demonstrating NCF4's crucial role in facilitating cell-cell contact between immune cells and intestinal cells, and mediating the paracrine effects of inflammatory cytokines and ROS. This coordination of the signaling network helps create a robust immune microenvironment that effectively prevents epithelial cell mutagenesis and tumorigenesis during the early stage of colitis-associated CRC.

PCN‐134(Fe)‐Gated Organic Photoelectrochemical Transistor with Unique Dual‐Directional Signaling

AbstractRecently, increasing attention has been paid to exploring the unique characteristics of newly emerged organic photoelectrochemical transistors (OPECT) for biological application and neuromorphic engineering due to their effectiveness for light‐driven ionic regulation of channels interfaced with rich biochemical reactions. The observation of interesting signaling reversion is reported—the realization of dual‐directional signaling with enhanced signal resolution—enabled by porous coordination networks (PCN)‐134(Fe) in the presence of varying H2O2 concentrations, which is totally different from exiting unidirectional signaling in OPECT. The underlying mechanism of such behavior is attributed to the change in the polarity of the gate photocurrent and is explained from the perspective of potential distribution. The practical application of this device is then studied by detecting the phorbol myristate acetate (PMA)‐induced secretion of H2O2 from three kinds of human breast cells. This study features the realization of dual‐directional signaling, which is expected to catalyze a new category of OPECT operation with unknown possibilities.

Special issue series: Advancing wild bee research and conservation through standardized methods

This introductory piece offers an overview of the seven accompanying papers featured in this special issue, a product of the U.S. Native Bee Monitoring Research and Coordination Network.

Research on energy interactive operation optimization strategy of multi-energy network with integrated energy based on cooperative game

Abstract Integrated energy includes multi-energy networks such as electricity, gas, cold, and heat. Horizontal multi-energy coordination and vertical source network storage load interaction can effectively support large-scale new energy consumption. In this paper, a multi-energy flow model of the integrated energy multi-energy network is constructed, an optimization model of energy sharing and mutual benefit of the multi-energy network is established based on Nash negotiation, and then the model is solved to obtain the optimal distribution scheme of cooperation benefits. Finally, a numerical example is given to verify the proposed energy sharing and mutual benefit method. The results show that the total power generation cost of each park is reduced by 27%, and the profit distribution of each park is more reasonable.

Analisis Pengaruh Penerapan SIMRS Terhadap Kinerja Pegawai di Unit Rawat Jalan RSUD X

Hospital Management Information System abbreviated as SIMRS is an information technology system that is a system that can process everything in the hospital in the form of coordination networks, reporting and administrative procedures to obtain precise and accurate information. SIMRS is one of the components that can affect employee performance where SIMRS helps employees in completing all services. The purpose of this study was to see the effect of SIMRS in improving employee performance. This research uses quantitative research with descriptive methods conducted at Arifin Achmad Hospital, Riau Province. This research was conducted through distributing questionnaires with 67 respondents, namely Outpatient Employees of RSUD Arifin Achmad Riau Province who use SIMRS. The results of this study obtained from the processing of research data show that the influence of SIMRS has a significant effect on the Performance of the Outpatient Unit of the Arifin Achmad Hospital Riau Province. This can be seen with a sig value of 0.002 <0.05.

Pushing the boundaries for fuel discovery with a multiview features fusion approach

AbstractGlobal warming poses a serious challenge to the human environment, prompting us to rapidly develop new environmentally friendly fuels. However, the time and cost required to determine the physical properties of fuels are constrained by the related industries. In this paper, we propose a multiview features fusion method based on neural networks. This method uses the eight graph neural networks models as the basis of the multichannel network coordinator to extract the compound's molecular feature; also the functional groups in the compound are embedded with molecule weight as functional groups feature, and finally, combining the molecular view with the functional groups view for the prediction of compound flash point (FP). We used a data set consisting of 2200 hydrocarbons and oxygenated compounds for model training and testing. The results show that the model performance is improved in both after feature fusion. Finally, the ablation experiments demonstrate that the use of this method is effective and provides a new idea for fast and accurate screening of fuels. The Attentive FP‐FG model was the most effective, with a mean absolute error of 4.395 K, root mean square error of 5.854 K, and R‐squared score (R2) of 0.986.

Coordination Networks from [Te4]2+ Clusters and Polynitriles

AbstractThe reactions of a series of organic polynitriles with [Te4][AsF6]2 in liquid SO2 solution lead either to reduction of [Te4]2+ to elemental tellurium or to the formation of coordination polymers. With 1,3‐dicyanobenzene (1,3‐DCB), 1,4‐dicyanobenzene (1,4‐DCB), 1,2,4,5‐tetracyanobenzene (TCB), tetracyanoethylene (TCNE) and tetracyanochinodimethane (TCNQ) the coordination complexes [Te4][AsF6]2 ⋅ 2(1,3‐DCB), [Te4][AsF6]2 ⋅ 3(1,4‐DCB) ⋅ 2SO2, [Te4][AsF6]2 ⋅ TCB, [Te4][AsF6]2 ⋅ TCNE and [Te4][AsF6]2 ⋅ TCNQ ⋅ 8 SO2 were isolated and characterized by crystal structure analyses and vibrational Raman spectroscopy. The nitriles are coordinated to the square‐planar clusters forming 1D chains, 2D arrangements and 3D networks. Tetrakis(dicyanomethylene)cyclobutendiide [C4(C{CN}2)4]2− is oxidized by [Te4]2+ to the neutral cyanocarbon C4(C{CN}2)4, structurally representing a 4[radialene]. The ionization potentials and electron affinities of the cyanamide anion, cyanogen, 1,2‐DCB, 1,3‐DCB, 1,4‐DCB, TCB, C4(C{CN}2)4, TCNE and TCNQ and those polynitriles, which cause reduction of [Te4]2+, were calculated at coupled‐cluster level of theory in order to examine possible reasons for the stability of the coordination polymers based on electronic properties of the nitriles.

Early diagnosis of Alzheimer’s disease using a group self-calibrated coordinate attention network based on multimodal MRI

Convolutional neural networks (CNNs) for extracting structural information from structural magnetic resonance imaging (sMRI), combined with functional magnetic resonance imaging (fMRI) and neuropsychological features, has emerged as a pivotal tool for early diagnosis of Alzheimer’s disease (AD). However, the fixed-size convolutional kernels in CNNs have limitations in capturing global features, reducing the effectiveness of AD diagnosis. We introduced a group self-calibrated coordinate attention network (GSCANet) designed for the precise diagnosis of AD using multimodal data, including encompassing Haralick texture features, functional connectivity, and neuropsychological scores. GSCANet utilizes a parallel group self-calibrated module to enhance original spatial features, expanding the field of view and embedding spatial data into channel information through a coordinate attention module, which ensures long-term contextual interaction. In a four-classification comparison (AD vs. early MCI (EMCI) vs. late MCI (LMCI) vs. normal control (NC)), GSCANet demonstrated an accuracy of 78.70%. For the three-classification comparison (AD vs. MCI vs. NC), it achieved an accuracy of 83.33%. Moreover, our method exhibited impressive accuracies in the AD vs. NC (92.81%) and EMCI vs. LMCI (84.67%) classifications. GSCANet improves classification performance at different stages of AD by employing group self-calibrated to expand features receptive field and integrating coordinated attention to facilitate significant interactions among channels and spaces. Providing insights into AD mechanisms and showcasing scalability for various disease predictions.

Optimal energy generation of hybrid energy systems considering economic and environmental multi-objective functions

This research is dedicated to exploring and identifying the most effective design for an energy source tailored specifically to meet the electricity demands of a residential community. In an era where energy efficiency and sustainability are paramount, this study emphasizes the importance of both technical and economic considerations in energy sourcing. It posits that any viable solution must not only be efficient in its energy production and consumption but also reliable in its delivery and financially feasible for the residents who will depend on it. To address this multifaceted challenge, the study proposes the innovative use of a rotation-invariant coordinate convolutional neural network in conjunction with binary battle royale optimization techniques. These advanced methodologies are selected for their potential to enhance the modelling and optimization processes involved in energy source design. The primary goal of employing these methods is to minimize two critical factors: the net present cost of the energy system and the overall energy cost incurred by the residents. By focusing on these objectives, the research aims to ensure that the proposed energy solutions are not only cost-effective but also sustainable over the long term. To rigorously test the proposed model and evaluate its performance, the research is conducted using the MATLAB platform. The study employs established methodologies and performance metrics to assess the outcomes of the model, ensuring that the findings are both credible and applicable to real-world scenarios. Through comprehensive testing and detailed analysis, this research aims to provide significant insights and actionable recommendations for the optimal design of energy sources in residential areas. By contributing to the ongoing discourse on sustainable energy solutions, the study seeks to inform policymakers, energy planners, and community stakeholders about effective strategies for meeting residential energy demands while promoting environmental sustainability. Ultimately, the findings of this research could play a crucial role in shaping the future of energy sourcing in residential communities, paving the way for more resilient and sustainable energy systems

Stability Assessment in Aqueous and Organic Solvents of Metal-Organic Framework PCN 333 Nanoparticles through a Combination of Physicochemical Characterization and Computational Simulations.

Mesoporous metal-organic frameworks (MOFs) have been recognized as powerful platforms for drug delivery, especially for biomolecules. Unfortunately, the application of MOFs is restricted due to their relatively poor stability in aqueous media, which is crucial for drug delivery applications. An exception is the porous coordination network (PCN)-series (e.g., PCN-333 and PCN-332), a series of MOFs with outstanding stability in aqueous media at the pH range from 3 to 9. In this study, we fabricate PCN-333 nanoparticles (nPCN) and investigate their stability in different solvents, including water, ethanol, and methanol. Surprisingly, the experimental characterizations in terms of X-ray diffraction, Brunauer-Emmett-Teller (BET), and scanning electron microscopy demonstrated that nPCN is not as stable in water as previously reported. Specifically, the crystalline structure of nPCN lost its typical octahedral shape and even decomposed into an irregular amorphous form when exposed to water for only 2 h, but not when ethanol and methanol were used. Meanwhile, the porosity of nPCN substantially diminished while being exposed to water, as demonstrated by the BET measurement. With the assistance of computational simulations, the mechanism behind the collapse of PCN-333 is illuminated. By molecular dynamics simulation and umbrella sampling, we elucidate that the degradation of PCN-333 occurs by hydrolysis, wherein polar solvent molecules initiate the attack and subsequent breakage of the metal-ligand reversible coordination bonds.

A Guideline for Local Elderly Policy Development in Thailand

In previous local elder policy research, most studies were fragmented with only some subjects or some steps in the policy process and attention to the local policy process not included explicitly. This article aims to analyze Thai local elderly policy formulation, implementation and evaluation and to propose guidelines for Thai local elderly policy development. This was a qualitative study. Data were collected using in-depth interviews with 40 key informants from 5 local case studies and 8 national organizations, as well as observations and documentary studies. Data were analyzed using thematic analysis and analytic induction. For the policy content dimensions, the guidelines of policy content development of the case studies aim to make senior citizens happy, self-sufficient, and physically and mentally healthy. The means to achieve this are comprised of the following:1) an economic, career, and income stability dimension; 2) a health dimension; and 3) a social dimension. For the policy process dimensions, the guideline of policy formulation comprises of the following: the related national policy dimension, including developing the mindset of policy actors, developing the content of policies with clarity that is up-to-date and congruent with key agreements or related principles, and developing a participation process and communication of the policy. The local policy dimension is locally aged society strategic planning based on strategic management and objectives and key results (OKRs) derived from the results of data analysis, integration of public policy theory, resource-based view in strategic management theory, and objective and key results to reduce the limitations of the public policy theory and model. This comprises developing policy actors’ mindsets, competencies, and motivations, collecting information, creating participation for analyzing and formulating direction, and making local elderly society strategic plans. The guidelines of policy implementation comprise the following: creating knowledge and understanding, organizing a central organization, implementing a strategic plan, formulating strategies for implementing and integrating amicable coordination of networks, seeking and allocating tangible and intangible resources, developing competencies of local government personnel, network partners, and target groups, creating and developing a culture supporting the aged society, and creating internal and external motivation. The guidelines of policy evaluation comprise the following: the development of the evaluation competency, the growth and ethical mindset, and the development of a participatory local policy evaluation system. Based on the results of this study, the guidelines focus on the intangible resources, the internal motivation, the mindset of policy actors, the coordination and strength of networks, and the upper-level policy factors.

Contrastive Learning based Speech Spoofing Detection for Multimedia Security in Edge Intelligence

Artificial intelligence (AI) empowered edge computing has given rise to a new paradigm and effectively facilitated the promotion and development of multimedia applications. The speech assistant is one of the significant services provided by multimedia applications, which aims to offer intelligent interactive experiences between humans and machines. However, malicious attackers may exploit spoofed speeches to deceive speech assistants, posing great challenges to the security of multimedia applications. The limited resources of multimedia terminal devices hinder their ability to effectively load speech spoofing detection models. Furthermore, processing and analyzing speech in the cloud can result in poor real-time performance and potential privacy risks. Existing speech spoofing detection methods rely heavily on annotated data and exhibit poor generalization capabilities for unseen spoofed speeches. To address these challenges, this paper first proposes the Coordinate Attention Network (CA2Net) that consists of coordinate attention blocks and Res2Net blocks. CA2Net can simultaneously extract temporal and spectral speech feature information and represent multi-scale speech features at a granularity level. Besides, a contrastive learning-based speech spoofing detection framework named GEMINI is proposed. GEMINI can be effectively deployed on edge nodes and autonomously learn speech features with strong generalization capabilities. GEMINI first performs data augmentation on speech signals and extracts conventional acoustic features to enhance the feature robustness. Subsequently, GEMINI utilizes the proposed CA2Net to further explore the discriminative speech features. Then, a tensor-based multi-attention comparison model is employed to maximize the consistency between speech contexts. GEMINI continuously updates CA2Net with contrastive learning, which enables CA2Net to effectively represent speech signals and accurately detect spoofed speeches. Extensive experiments on the ASVspoof2019 dataset show that GEMINI reduces the Equal Error Rate and tandem Detection Cost Function by up to 96.75% and 96.35% in the physical access scenario, and by up to 86.62% and 87.71% in the logical access scenario compared to peer methods.

Ammonia Storage in Metal-Organic Framework Materials: Recent Developments in Design and Characterization.

Since the advent of the Haber-Bosch process in 1910, the global demand for ammonia (NH3) has surged, driven by its applications in agriculture, pharmaceuticals, and energy. Current methods of NH3 storage, including high-pressure storage and transportation, present significant challenges due to their corrosive and toxic nature. Consequently, research has turned towards metal-organic framework (MOF) materials as potential candidates for NH3 storage due to their potential high adsorption capacities and structural tunability. MOFs are coordination networks composed of metal nodes and organic linkers, offering unprecedented porosity and surface area, and allowing incorporation of various functional groups and metal sites that can enhance NH3 adsorption. However, the stability of MOFs in the presence of NH3 is a significant concern since many degrade upon exposure to NH3, primarily due to ligand displacement and framework collapse. To address this, recent studies have focused on the synthesis and postsynthetic modification of MOFs to enhance both NH3 uptake and stability. In this Account, we summarize recent developments in the design and characterization of MOFs for NH3 storage. The choice of metal centers in MOFs is crucial for stability and performance. High-valence metals such as AlIII and TiIV form strong metal-linker bonds, enhancing the stability of the framework to NH3. The MFM-300 series of materials composed of high-valence 3+ and 4+ metal ions and carboxylic linkers demonstrates high stability and high NH3 uptake capacities. Ligand functionalization is another effective strategy for improving the NH3 adsorption. Polar functional groups such as -NH2, -OH, and -COOH enhance the interaction between the framework and NH3, particularly at low partial pressures, while postsynthetic modification allows fine-tuning of these functionalities to optimize the framework for higher adsorption capacities and stability. For example, MFM-303(Al), incorporating free carboxylic acid groups, exhibits a high NH3 packing density comparable to that of solid NH3. Creating defect sites by removing linkers or adding metal ions increases the number of active sites available for NH3 adsorption and shows promise for enhancing uptake. UiO-66, a stable MOF framework, can be modified to include defect sites, significantly enhancing the level of NH3 uptake. The full characterization of MOFs and especially their interactions with NH3 are vital for understanding and improving their performance. Techniques such as neutron powder diffraction (NPD), inelastic neutron scattering (INS), diffuse reflectance infrared Fourier transform spectroscopy (DRIFTS), electron paramagnetic resonance (EPR) spectroscopy, and solid-state nuclear magnetic resonance (ssNMR) spectroscopy can elucidate host-guest interactions and binding dynamics between NH3 and the framework structure and afford crucial information for the future design and rational development of new sorbents. This Account highlights our current strategies for the synthesis and characterization of MOFs for NH3 capture, providing an overview of this rapidly evolving field.

Analysis of Relay Coordination in Electrical Distribution Networks with Optimally Positioned Distributed Generation Units

As power demand increases and transmission and distribution capacity is limited, Distributed Generation (DG) units are gradually being incorporated into electrical power distribution networks. However, this integration may result in a significant impact on the coordination of protective relays, potentially generating issues such as blindness of protection and false tripping of overcurrent relays. To overcome these issues, an adaptive protection method is presented that adjusts relay sensitivity in response to changes in network design. The suggested technique dynamically modifies relay settings based on the line current, which fluctuates depending on the system design. Digital relays are needed for this method in order to save operational data in real time. Based on periodic observations, the Plug Multiplier Setting (PMS) and Time Multiplier Setting (TMS) parameters are optimized using a Fuzzy Inference System (FIS). Fuzzy rules are used by the adaptive algorithm for every relay. These rules are produced using the fuzzy editor using the inputs provided. An initial investigation was carried out to evaluate the effect of DG on the coordination of relay protection., as well as the optimal placement of DG to reduce losses and improve voltage profiles, using two base distribution networks. The algorithm was further tested on various configurations of IEEE distribution networks, and its effectiveness in achieving optimal relay coordination with adaptive settings was validated through the relay coordination module in ETAP.

An improved ResNet method for urban flooding water depth estimation from social media images

Social media images featuring high timeliness, large data volume, and low cost, is utilized for flooding depth estimation. Common flood depth estimation methods are to segment each reference instance, resulting in local water depths and contradictory results. This study added Coordinate Attention into Residual Neural Network (ResNet), and proposed Coordinate Attention-Residual Neural Network (CA-ResNet) to acquire global submerged water depths. The 2021 Henan rainstorm in China was used as case study and a flooding dataset from Chinese Sina Microblog was constructed, with total 5676 images and 4189 flooded. All the flooded depths class 0–9 reflected from the images were annotated manually. The proposed CA-ResNet method was compared with VGGNet, ResNet, GoogleNet, and EfficientNet, both accuracy and F1 score improved by 1% − 3%. The average accuracy of level 0–––8 within the error range of CA-ResNet reached 83.14%. It is proved that CA-ResNet could achieve flood depth estimation, facilitating efficient decision support for flood responding.

[Cu(en)2]2+ - [W(CN)6(bpy)]2- interactions in cyanido bridged and not linked complexes – structural study

Five heterobimetallic Cu(II)-W(IV) complexes with the general formulas [Cu(en)2][W(CN)6(bpy)], {[Cu(en)2][W(CN)6(bpy)]}2∙[Cu(en)2(H2O)2]X2 (where X = Cl or Br), Na4K2[Cu(en)2][W(CN)6(bpy)]4, Li2[Cu(en)2(H2O)2][W(CN)6(bpy)]2 were synthesized and described by elemental analyses, magnetic measurements, IR and UV–Vis spectra, as well as the single crystal X-ray structure measurements. In structures, the copper atoms adopt the geometry of a slightly distorted octahedron. The effect of the addition of a halogen or alkali metal on the different modes of cyanide bridging in all structures was discussed. These results provide an important contribution to the knowledge on the controllable synthesis of coordination networks based on cyanide bridges.

Examining Care Network Characteristics in Older Adults' Relocation to Residential Care Settings.

When older adults face increasing care needs or limited support, remaining safely and comfortably at home becomes challenging. Extant research has primarily concentrated on characteristics of the older adult or their primary caregiver on nursing home admission. This study examines the risk of older adults transitioning to residential care (e.g., assisted living, nursing home), focusing on the influence of their care network or involvement of multiple helpers. Using the National Health and Aging Trends Study, we conducted competing risk regression models that account for mortality, following 7,085 initially community-dwelling older adults across Rounds 1-9 (2011-2019). We assessed network composition, size, shared tasks, and the number of in-network specialists or generalists while controlling for individual sociodemographic and health factors. Individuals with care networks that shared medical tasks had the highest risk of moving to a residential care setting, followed by those sharing household tasks. Conversely, shared mobility or self-care and transportation responsibilities were associated with lower risks. Having more generalists, but not specialists, increased the risk. Larger networks were associated with heightened risk, although having close family members like a spouse was protective. The findings underscore that care network characteristics are critical to older adults' ability to age in place. Specifically, older adults with larger networks, lacking a spouse or child, and providing complex care are at greater risk for relocating. Understanding care networks can guide interventions related to care network coordination and resource allocation to help avoid or postpone a residential care move.

Research on a Method for Identification of Peanut Pests and Diseases Based on a Lightweight LSCDNet Model.

Timely and accurate identification of peanut pests and diseases, coupled with effective countermeasures, is pivotal for ensuring high-quality and efficient peanut production. Despite the prevalence of pests and diseases in peanut cultivation, challenges such as minute disease spots, the elusive nature of pests, and intricate environmental conditions often lead to diminished identification accuracy and efficiency. Moreover, continuous monitoring of peanut health in real-world agricultural settings demands solutions that are computationally efficient. Traditional deep learning models often require substantial computational resources, limiting their practical applicability. In response to these challenges, we introduce LSCDNet (Lightweight Sandglass and Coordinate Attention Network), a streamlined model derived from DenseNet. LSCDNet preserves only the transition layers to reduce feature map dimensionality, simplifying the model's complexity. The inclusion of a sandglass block bolsters features extraction capabilities, mitigating potential information loss due to dimensionality reduction. Additionally, the incorporation of coordinate attention addresses issues related to positional information loss during feature extraction. Experimental results showcase that LSCDNet achieved impressive metrics with accuracy, precision, recall, and Fl score of 96.67, 98.05, 95.56, and 96.79%, respectively, while maintaining a compact parameter count of merely 0.59 million. When compared with established models such as MobileNetV1, MobileNetV2, NASNetMobile, DenseNet-121, InceptionV3, and X-ception, LSCDNet outperformed with accuracy gains of 2.65, 4.87, 8.71, 5.04, 6.32, and 8.2%, respectively, accompanied by substantially fewer parameters. Lastly, we deployed the LSCDNet model on Raspberry Pi for practical testing and application and achieved an average recognition accuracy of 85.36%, thereby meeting real-world operational requirements.