Local Network Research Articles

Modeling The Evolution of Community Structure by the Dynamic Network Analysis: Sustainability Transition in Kyoto Eco-School Districts, Japan

Sustainability transition increasingly relies on local institutional settings and community-based efforts where local agencies play pivotal roles. A significant gap lies in understanding the dynamic interplay among community-based organizations over time that shape evolving strategic collaborations in different stages to drive local institutional change. This study adopts a dynamic network approach to map the evolving community structure, identify key organizations, and detect collaboration patterns among local actors by the case study of Kyoto, Japan. Furthermore, it explores the influence of significant events and policies on the network evolution. The study uncovers three main findings. Firstly, a three-stage evolution of the local network is concluded that presents incremental change towards an expanding, decentralized community structure, forming collaborative governance. Secondly, five collaboration patterns and their dynamics are revealed, reflecting evolving strategic alliances that play different roles in leveraging resources throughout the process. Thirdly, the effects of policies and events on the network are well reflected and explained through matching the time series data. The Kyoto case uncovers hidden community dynamics that illuminate local pathways to sustainable practices, offering guidance for policymaking and practices that resonate more broadly with globally relevant contexts.

Automated Hematoma Detection and Outcome Prediction in Patients With Traumatic Brain Injury

ABSTRACTPurposeTo develop a tool for automated subtype classification and segmentation of intracranial hemorrhages (ICH) on CT scans of patients with traumatic brain injury (TBI). Furthermore, outcome prediction for patients can effectively facilitate patient management.MethodsThis study presents a cascade framework for two‐stage segmentation and multi‐label classification. The hematoma region of interest (ROI) is localized, and then the ROI is cropped and resized to the original pixel size before being input into the model again to obtain the segmentation results. In multilabel classification, the mask obtained from automatic segmentation is superimposed onto the corresponding ROI and CT slices, respectively, to constitute the input image. Subsequently, the ROI image is employed as the local network input to obtain local features. Third, the CT image is utilized to construct a feature extraction network to obtain global features. Ultimately, the local and global features are fused dimensions in the pooling layer, and calculated to generate the final retrieval results. For the prediction of 14‐day in‐hospital mortality, automatically extracted hematoma subtype and volume features were integrated to enhance the widely used CRASH model.ResultsThe proposed segmentation method achieves the best estimates on the Dice similarity coefficient and Jaccard Similarity Index. The proposed multilabel classification method achieved an average accuracy of 95.91%. For mortality prediction, the best model achieved an average area under the receiver operating characteristic curve (AUC) of 0.91 by 5‐fold cross‐validation.ConclusionsThe proposed method enhances the precision of hematoma segmentation and subtype classification. In clinical settings, the method can streamline the evaluation of ICH for radiologists, and the automatically extracted features are anticipated to facilitate prognosis assessment.

MR_NET: A Method for Breast Cancer Detection and Localization from Histological Images Through Explainable Convolutional Neural Networks

Breast cancer is the most prevalent cancer among women globally, making early and accurate detection essential for effective treatment and improved survival rates. This paper presents a method designed to detect and localize breast cancer using deep learning, specifically convolutional neural networks. The approach classifies histological images of breast tissue as either tumor-positive or tumor-negative. We utilize several deep learning models, including a custom-built CNN, EfficientNet, ResNet50, VGG-16, VGG-19, and MobileNet. Fine-tuning was also applied to VGG-16, VGG-19, and MobileNet to enhance performance. Additionally, we introduce a novel deep learning model called MR_Net, aimed at providing a more accurate network for breast cancer detection and localization, potentially assisting clinicians in making informed decisions. This model could also accelerate the diagnostic process, enabling early detection of the disease. Furthermore, we propose a method for explainable predictions by generating heatmaps that highlight the regions within tissue images that the model focuses on when predicting a label, revealing the detection of benign, atypical, and malignant tumors. We evaluate both the quantitative and qualitative performance of MR_Net and the other models, also presenting explainable results that allow visualization of the tissue areas identified by the model as relevant to the presence of breast cancer.

Spatiotemporal wind speed forecasting using conditional local convolution and multidimensional meteorology features

Wind speed prediction is crucial for precisely wind power forecasting and reduced maintenance costs. Highland regions, which possess a considerable wind potential, present complex meteorological conditions, making wind speed prediction challenging. Traditional weather forecasting relies on complex statistical methods and extensive prior knowledge. While recent deep learning models have improved prediction accuracy, they often assume uniform influence weight structure, limiting model effectiveness. This study introduces an enhanced Conditional Local Convolution Recurrent Network (CLCRN) model to improve spatiotemporal wind speed forecasting using multidimensional meteorological inputs such as temperature, pressure, and dew point, alongside wind components. This model addresses uniform influence model weight issue by redesigning convolution kernels to better capture local meteorological features and integrating multiple influencing factors. Our model consistently achieves lower Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) values across various prediction intervals (3, 6, 9, and 12 h) compared to other models, supported by the meteorological station data from 2019 to 2021. Furthermore, the spatial distribution of the local convolution weights aligns with local wind velocity patterns in Inner Mongolia, enhancing model interpretability. These results demonstrate potential for practical applications in renewable energy planning and wind dynamics simulation.

Decoding the human prenatal immune system with single-cell multi-omics.

The human immune system is made up of a huge variety of cell types each with unique functions. Local networks of resident immune cells are poised to sense and protect against pathogen entry, whereas more widespread innate and adaptive immune networks provide first rapid, then long-lasting and targeted responses. However, how we develop such a diverse and complex system remains unknown. Studying human development directly has been challenging in the past, but recent advances in single-cell and spatial genomics, together with the co-ordinated efforts of the Human Cell Atlas and other initiatives, have led to new studies that map the development of the human immune system in unprecedented detail. In this Review, we consider the timings, transitions, cell types and tissue microenvironments that are crucial for building the human immune system. We also compare and contrast the human system with model species and in vitro systems, and discuss how an understanding of prenatal immune system development will improve our knowledge of human disease.

Alleviating the resolution limit problem in spatial community detection: a local network structure-based method

Spatial community detection plays a crucial role in the analysis of spatially embedded networks. However, most existing methods adopt modularity as an objective function, which may fail to detect small spatial communities (i.e. the well-known resolution-limit problem). To alleviate this problem, a local network structure-based spatially constrained Leiden method was developed. First, the weights of the edges were reset based on the local network structure, which facilitated a clearer delineation between distinct communities. Second, we extended Leiden, an effective community detection method, to spatial community detection content by adding spatial constraints. Experiments on simulated datasets demonstrated that the proposed method is superior to four state-of-the-art methods for detecting spatial communities of different sizes. A case study conducted using the Shenzhen taxi dataset demonstrated that the proposed method outperformed four state-of-the-art methods in revealing urban spatial structures. Notably, the modularity of the spatial communities detected using the proposed method exhibited a marked improvement, nearly doubling that of the four comparative methods in the case study. This study presents a novel and promising framework for detecting spatial communities using modularity.

Performance Analysis of Millimeter-Wave Propagation Characteristics for Various Channel Models in the Indoor Environment

Due to the recent surge in the proliferation of smart wireless devices that feature higher data speeds, there has been a rise in demand for faster indoor data communication services. Moreover, there is a sharp increase in the amount of mobile data being generated worldwide, and much of this data comes from residential wireless applications like high-definition TV, device-to-device communication, and high data rate indoor networks (i.e., local and cellular). These technologies need large capacity, high data rate indoor wireless networks with huge bandwidth. Consequently, a greater interest exists in implementing an effective and trustworthy indoor propagation model for next-generation wireless systems operating in the massively bandwidth-rich millimeter wave (mm-wave) frequency range. The analysis of mm-wave propagation characteristics in an indoor environment using the ray tracing approach is proposed in this paper. Propagation modeling for 60 GHz bands is included. The aspects of wideband propagation characteristics such as angular spread, path loss, delay spread, and power delay profile are modeled in this paper. The position of transceivers, antenna effect, and attenuation, in the hallways, and stairwells will all be considered while determining the propagation parameters. This includes wave propagation characteristics like absorption, reflection, and diffraction by building structures and furniture. The specifications for propagation characteristics are included in the article for developing indoor local and cellular networks. In this paper, the IRT model has been tested at 60 GHz for potential mobile communication and is identified as the best method for predicting signal attenuation caused by objects, barriers, or humans within buildings in internal millimeter wave transmission.

Superior performance of a center-point AI model over VFLDNet in automated cobb angle estimation for scoliosis assessment.

Aims to establish the superiority of our proposed model over the state-of-the-art vertebra-focused landmark detection network (VFLDNet) in automating Cobb angle estimation from spinal radiographs. Utilizing a private dataset for external validation, we compared the performance of our center-point detection-based vertebra localization and tilt estimation network (VLTENet) with the key-point detection-based VFLDNet. Both models' Cobb angle predictions were rigorously evaluated against manual consensus score using metrics such as mean absolute error (MAE), correlation coefficient, intraclass correlation coefficient (ICC), Fleiss' kappa, Bland-Altman analysis, and classification metrics [sensitivity (SN), specificity, accuracy] focusing on major curve estimation and scoliosis severity classification. A retrospective analysis of 118 cases with 342 Cobb angle measurements revealed that our model achieved a MAE of 2.15° for total Cobb angles and 1.89° for the major curve, significantly outperforming VFLDNet's MAE of 2.80°and 2.57°, respectively. Both models demonstrated robust correlation and ICC, but our model excelled in classification consistency, particularly in predicting major curve magnitude (ours: kappa = 0.83; VFLDNet: kappa = 0.67). In subgroup analyses by scoliosis severity, our model consistently surpassed VFLDNet, displaying superior mean (SD) differences, narrower limits of agreement, and higher SN, specificity, and accuracy, most notably in moderate (ours: SN = 86.84%; VFLDNet: SN = 83.16%) to severe (ours: SN = 92.86%; VFLDNet: SN = 85.71%) scoliosis. Our model emerges as the superior choice for automated Cobb angle estimation, particularly in assessing major curve and moderate to severe scoliosis, underscoring its potential to revolutionize clinical workflows and enhance patient care.

Assessment of Borač-Kotlenik magmatic massif rock mass technical properties as potential source for optimal development of regional road infrastructure based on local stone materials

The Borač-Kotlenik magmatic massif in central Serbia is mainly made up of effusive and pyroclastic rocks, formed in three main phases of volcanic activity: 1. dacite and andesite, 2. quartz-latite and dacite, and 3. basaltoid rocks. Rock mass samples from this magmatic massif have been examined and mined in numerous localities during the XX century for purposes of building and reconstruction works of local and regional road networks. The examination process continues today for purposes of ‘Morava corridor’ highway building and its demand for the local stone material of the specified quality. The results of rock mass technical properties' tests have shown that its quality for road building purposes depends significantly on petrologic type, soundness, and hydrothermal alteration type. Oxidation alteration types can cause a significant decrease in compressive strength, an increase in porosity and water absorption, especially as oxidation chemical processes cause increased susceptibility to weathering, thus making the rock mass unusable in road construction profile layers above the embankment. Testing results demonstrate that effusive volcanic rocks of the Borač-Kotlenik magmatic massif generally can be used in the road building process. For this purpose, it is necessary to select the conformable rock mass zones at each locality, where hydrothermal alteration and weathering products are absent in order to obtain the best available stone material of volcanic origin.

Loneliness and Social Isolation: qualitative study among youth in vulnerable situations

Abstract Background Loneliness and social isolation are increasing among young people, particularly those in vulnerable NEET (Not in Education, Employment or Training) situations, potentially leading to poor health and well-being outcomes. We aim to explore these challenges from the perspective of NEET youngsters and link workers who support them in co-creating individual action plans for their social and economic integration. Methods Data were collected through in-depth and semi-structured interviews with 15 young people in NEET situations, aged 18-34, and 7 link workers from several social organisations in rural and urban areas in Portugal. The young participants were selected based on their age, educational level, mental health needs, and urban/rural regions. Thematic analysis was used to analyse the interviews. Results The results showed a convergence between the perspectives of young people and link workers on the factors that influence social isolation and loneliness, including social and emotional skill deficits, excessive use of social media platforms, and mental health problems. Young people reported to being heavily involved in social media platforms, which often did not translate into meaningful relationships in real life. Youngsters also highlighted the lack of local support and community resources in rural areas. Link workers identified specific challenges young migrants face in community integration, including language barriers (for the youth with a migrant origin) and lack of familiarity with local resources. Conclusions This study highlights social media platforms, mental health and social and emotional skill deficits as main factors contributing to the social isolation and loneliness of young people in a NEET situation. This emphasizes the importance of integrated proximity-based interventions that incorporate community resource mapping and local support networks, including mental health support services, and promote multi-sector collaboration. Key messages • Social media platforms, mental health needs, and social and emotional skill deficits drive social isolation in NEET youth, stressing integrated, community-focused interventions. • Proximity-based strategies with community mapping and mental health support enhance NEET youths’ social integration, urging cross-sector collaboration.

Air quality modeling intercomparison and multiscale ensemble chain for Latin America

Abstract. A multiscale modeling ensemble chain has been assembled as a first step towards an air quality analysis and forecasting (AQF) system for Latin America. Two global and three regional models were tested and compared in retrospective mode over a shared domain (120–28° W, 60° S–30° N) for the months of January and July 2015. The objective of this experiment was to understand their performance and characterize their errors. Observations from local air quality monitoring networks in Colombia, Chile, Brazil, Mexico, Ecuador and Peru were used for model evaluation. The models generally agreed with observations in large cities such as Mexico City and São Paulo, whereas representing smaller urban areas, such as Bogotá and Santiago, was more challenging. For instance, in Santiago during wintertime, the simulations showed large discrepancies with observations. No single model demonstrated superior performance over others or among pollutants and sites available. In general, ozone and NO2 exhibited the lowest bias and errors, especially in São Paulo and Mexico City. For SO2, the bias and error were close to 200 %, except for Bogotá. The ensemble, created from the median value of all models, was evaluated as well. In some cases, the ensemble outperformed the individual models and mitigated extreme over- or underestimation. However, more research is needed before concluding that the ensemble is the path for an AQF system in Latin America. This study identified certain limitations in the models and global emission inventories, which should be addressed with the involvement and experience of local researchers.

Inclusive Life Projects for people with Serious Mental Disorder and/or addictions

Abstract Project “Inclusive Life Projects” offers comprehensive and community care to people with SMD/A within projects of autonomous living, which provide a concrete and real response to their needs, with the ultimate objective of avoiding the risk of institutionalization. Currently, 26 actions have been designed and are being implemented within JA ImpleMENTAL pilot in five municipalities in the Region of Murcia: Caravaca, Cartagena, Lorca. Molina de Segura and Yecla with a participation of 50 people with SMD/A. The following elements are selected from the Belgian good practice: • Creation of local intersectoral networks promoting person-centered care process; • Personalization of care through the Individualized Care Plan, responding to the needs, and desires of people with SMI/A, activating the appropriate support; • Professional case manager. It generates the well-being of people on an empathy and trust basis and articulates coordination so that the agreed Plan can be developed as planned. A strategic and support coordination tool for action and facilitation of institutional support, the Social and Health Coordination Protocol for people with SMI/A, has been developed. The protocol facilitates the creation of coordination structures, among them the Socio-Health Coordination Base Teams stand out, teams made up of professionals from the different agents involved, multi-professional and intersectoral, (Mental Health, Primary Health Care, Social Services, Social Initiative) taking into account the needs of the person. It also serves to share information, detect training needs, influence resources, etc. PETRA, a computer platform, has been developed for sharing information between the systems involved, especially the health system and the social services system, both primary care, hospital care and specialized care. It allows the exchange of information, in real time, between professionals, the planning of actions, and the design of indicators and control and evaluation processes.

JA ImpleMENTAL Implementing the Belgian Best Practice on Community Mental Health system Reform

Abstract Mental health challenges affect more than one in six people across the EU. In order to support Member States to proceed with mental health care system transformation and suicide prevention JA ImpleMENTAL, was initiated on the request of Member States, on October 2021 under the European Union 3rd Health Program. The JA consists of 39 organizations from 21 countries, more than 180 persons are working. Two advisory bodies support the consortium and provide their insights and expertise, a stakeholder forum with 10 key European Organizations in Mental Health including EUPHA Mental Health Section and WHO Europe and OECD, and the Member State Policy Committee which ensures the involvement of ministries and enables the practices to be embedded in health systems. Within the 11 countries implementing pilots under the Belgium model using a common Implementation Strategy, a total 163 activities are implemented under the 5 following key areas: 62 on structural measures needed for the establishment of local networks promoting a user’s centered, human’s right based recovery approach, 43 for the development and/or transformation of mental health services, 22 on training & capacity building in support of the reform and cultural change, 22 on continuous communication, information and awareness raising, and 13 on data collection, monitoring and evaluation. An analysis of MS pilot action plans shows that most service transformation efforts have concentrated on: defining care pathways for people at risk and for those with mild to severe mental health conditions including smooth transition from child and adolescent to Adult Mental Health services, as well as from inpatient to community services, the nomination of case managers for assisting individuals to their recovery process the development of individual service plans, the Involvement of users in various layers of service delivery including peer support and the provision of assertive treatment through mobile units.

Buildings as Batteries

Aggregators are increasingly using portfolios of various end-user resources such as local renewable generation, batteries, EVs, and demand-side management to participate in the electricity markets as virtual power plants. Whilst the smart control of energy within buildings is well established for cost optimization, the prospect of an aggregator collaborating with the energy managers of buildings to trade electricity in the wholesale markets is under researched. This paper uses a state-of-the-art architectural simulator to model the thermal inertia of a typical high-rise building in London and represent the thermodynamics of its hourly occupancy and weather responses. The building is simulated as a virtual battery by manipulating the HVAC settings. Price arbitrage on the electricity wholesale market and contracting with the local distribution network for flexible reserve services are both feasible and profitable. It is concluded that aggregators can apparently use buildings as additional assets within their trading portfolios. JEL Classification: L85 and L94.

Evaluating the Availability and Accessibility of Agricultural Extension Services Under the Single Spine System in Uganda. A Case of Smallholder Crop Farmers in Buhweju District

Purpose: This study evaluated the availability and accessibility of agricultural extension services under the Single Spine System, with a specific focus on smallholder crop farmers in Buhweju District. Methodology: The study adopted a mixed-methods approach, employing both quantitative and qualitative data collection techniques. Structured questionnaires were administered to a sample of 393 smallholder crop farmers and key informant interviews with district agricultural officers and extension workers provided in-depth insights into the delivery of services. Findings: The results indicate that education was positively and significantly (P<0.01) associated with knowledge about the availability of extension services. Farmers with more years of schooling had a greater likelihood of being aware of extension providers. Similarly, larger households with more labor resources (median size = 4) had better access to extension services. Moreover, household land size (median = 3 acres) and income (median = UGX 250,000) were significantly correlated with both availability and access to extension services, with wealthier farmers seeking more information to improve agricultural productivity. The study also revealed that proximity to extension service centers was a critical factor; households closer to sub-county offices (median distance = 1.5 km) had higher knowledge of available services. Access to credit and group membership were also major determinants of both awareness and access to extension services. Challenges were also identified, including limited outreach by extension officers, inadequate allowances, and insufficient logistical support for field officers. Unique Contribution to Theory, Policy and Practice: The study recommends increased sensitization efforts using local leaders, social media, and community networks, alongside greater support for sub-county agricultural officers to ensure effective service delivery.

The Local Declines in Child SSI Applications and Awards During COVID

Child applications and awards for Supplemental Security Income (SSI) fell sharply at the outset of the COVID-19 pandemic. Cumulative applications from April to September 2020 were about 30% lower than applications over the same period in 2019 with substantial variation in rates of decline across local areas. In this article, we explore the factors correlated with the change in applications and awards across localities at the beginning of the pandemic. Our findings point to three particularly important factors influencing the magnitude of the change in applications and awards: (a) the restriction of in-person services in all Social Security Administration field offices in March 2020, (b) the pandemic’s disruptions to social and service networks through which people may learn about SSI, and (c) new economic stabilization policies, such as economic impact payments and supplemental unemployment insurance payments. These results highlight the substantial local variation in SSI participation. This variation is especially important in considering general issues around access to SSI, particularly for policies that aim to improve SSI access through outreach. Our findings underscore the importance of local networks in creating program awareness at local levels, and that they might be fruitful avenues for further outreach efforts.

Global induced local network for infrared: dim small target detection

Abstract It is challenging to detect infrared dim targets submerged in complicated backgrounds due to their small size and faint intensity. The previous attention-based detection networks frequently require global long-range dependence. Significant calculations are required to determine the target's sparse but meaningful position. To prevent wasting calculations on the background, this paper offers a detection network guided by global context for local feature learning, named GILNet (Global Induced Local Network). It designs a global location module (GLM) and a local feature interaction module (LFIM) to capture the global position and features of targets, respectively. More specifically, using global context interaction, the GLM finds the region that might contain dim small targets, that is, the coarse location. In the coarsely located regions, the LFIM further acquires feature information about targets. Next, we also design an eight-directional attention operation to obtain the contour information of targets in the low feature map. It is fused with the high feature map in the multi-directional feature fusion module (MFFM), which retains more semantic and spatial information about targets. Finally, quantitative and qualitative analysis show that the GILNet performs better than eight comparison methods on two public datasets.

Multi-source information fused loose particle localization and material identification method for sealed electronic equipment

Sealed electronic equipment are1 an important component of aerospace defense systems, and loose particles pose a significant threat to their reliable operation. Loose particle detection is crucial. For sealed electronic equipment with large scale and complex structure, loose particle detection should not only include the judgment of existence, but also obtain location and material information to facilitate the cleaning and control work. In this paper, the authors proposed a multi-source information fused loose particle localization and material identification method. Firstly, the equipment model was designed, the loose particle samples were made, and loose particle signals were collected. Secondly, the two-stage adaptive energy threshold pulse extraction algorithm was newly proposed to extract effective pulses, and the threshold-judgement-search pulse matching algorithm was improved to match the effective pulse groups. Next, spectrograms were transformed from effective pulses to create the localization and material image set. The time-domain, frequency-domain and gray-level co-occurrence matrix features were used to construct the joint feature library. Then, the channel-weighting feature selection method was used to create the localization and material data set. Finally, PReLU-VGG19-Plus was trained on the localization and material image set to obtain the optimal localization and material neural network, while parameter-optimized XGBoost was trained on the localization and material data set to obtain the optimal localization and material classifier. On this basis, combined with the triple majority voting process, the combined localization and material framework were constructed. Extensive test results show that, the location-identification achieved by combined localization framework and the material-identification accuracy achieved by combined material framework are all 100%. The feasibility, stability, and superiority of the method proposed in this paper have been fully verified. It is an important supplement to the existing loose particle detection research, providing important reference for signal detection and classification research in similar fields, and effectively improving the reliability of sealed electronic equipment.

How Connected Cars Could Capture Cloud Dynamics for Solar Forecasting—Evidence from Two Simulation Scenarios

The rapidly increasing share of fluctuating electricity from photovoltaics calls for accurate approaches to estimate cloud motion, the primary source for the varying power supply. While local sensor networks are prominent in targeting forecast horizons too short for image‐based methods, they have minimal spatial coverage. This work presents the first step towards expanding those approaches to spatially scalable sensor networks: With the motivation of using automotive light sensors as a sensor network, two excerpts from a microscopic traffic simulation serve as simulative sensor networks. A fractal‐based cloud shadow pattern passes the sensor network areas with defined velocities and directions, which shall be estimated using the cumulative mean absolute error method. The evaluation results indicate that the more extensive observation areas compensate for the dynamics in the sensor network when compared to a reference work with a static sensor grid. Furthermore, this work shows how the estimates deteriorate with lower vehicle penetration rates (PR) and longer building shadows due to a lower solar elevation angle. At a penetration rate of 40%, the root mean square errors for both sensor networks are still below 5 ms−1. In conclusion, the spatiotemporal characteristics of a vehicle network offer a potential for estimating cloud movements.

Combined Keyword Spotting and Localization Network Based on Multi-Task Learning

The advent of voice assistance technology and its integration into smart devices has facilitated many useful services, such as texting and application execution. However, most assistive technologies lack the capability to enable the system to act as a human who can localize the speaker and selectively spot meaningful keywords. Because keyword spotting (KWS) and sound source localization (SSL) are essential and must operate in real time, the efficiency of a neural network model is crucial for memory and computation. In this paper, a single neural network model for KWS and SSL is proposed to overcome the limitations of sequential KWS and SSL, which require more memory and inference time. The proposed model uses multi-task learning to utilize the limited resources of the device efficiently. A shared encoder is used as the initial layer to extract common features from the multichannel audio data. Subsequently, the task-specific parallel layers utilize these features for KWS and SSL. The proposed model was evaluated on a synthetic dataset with multiple speakers, and a 7-module shared encoder structure was identified as optimal in terms of accuracy, direction of arrival (DOA) accuracy, DOA error, and latency. It achieved a KWS accuracy of 94.51%, DOA error of 12.397°, and DOA accuracy of 89.86%. Consequently, the proposed model requires significantly less memory owing to the shared network architecture, which enhances the inference time without compromising KWS accuracy, DOA error, and DOA accuracy.