Local Network Research Articles

Is the ‘Protected Designation of Origin’ an indicator for sustainable landscape management? Insights from pasture-based animal husbandry in five EU countries

ABSTRACT Previous research has shown that products labeled as ‘Protected Designation of Origin’ (PDO) correlate positively with indicators for landscape sustainability. However, specific factors that turn PDO products into sustainable landscape management tools remain vague. We analyze interviews from six European production systems to explore the links between PDO-labeled products and sustainable landscape management. All case studies were linked to extensive animal husbandry. We found that PDO products can contribute to sustainable landscape management if well-adapted incentives for agri-environmental measures supplement income. Successful products are further associated with local networks that use synergies between different stakeholder interests. Due to their promotion of social-ecological goals at the landscape level, PDO products can be a powerful addition to the EU’s Green Deal and rural development strategy, and by introducing eligibility criteria that focus on social-ecological goals, PDO labeling could be classified as a sustainability standard.

Evaluation of a Local Heating Network Supplied by a Pyrolysis Plant

In order to mitigate climate change, a wide range of negative emission technologies, such as pyrolytic carbon capture and storage, must be used in the future. This study therefore examines a specific application example for the energy supply with a pyrolysis plant that is operated with locally available biomass in the smallest district of the city of Freiburg. It is shown that such a supply concept is feasible and that the economic efficiency of the supply concept depends on the system output as well as the amount of local biomass and the revenues from the sale of the biochar. Of the six pyrolysis plants examined, two proved to be a promising alternative to the current wood chip boiler. By switching to an energy supply with a pyrolysis plant, the district could save several hundred tons of CO2 per year. The resulting total negative emissions would amount to almost 1200 tons of CO2 per year.

Towards Few-Label Vertical Federated Learning

Federated Learning (FL) provided a novel paradigm for privacy-preserving machine learning, enabling multiple clients to collaborate on model training without sharing private data. To handle multi-source heterogeneous data, vertical federated learning (VFL) has been extensively investigated. However, in the context of VFL, the label information tends to be kept in one authoritative client and is very limited. This poses two challenges for model training in the VFL scenario: On the one hand, a small number of labels cannot guarantee to train a well VFL model with informative network parameters, resulting in unclear boundaries for classification decisions; On the other hand, the large amount of unlabeled data is dominant and should not be discounted, and it’s worthwhile to focus on how to leverage them to improve representation modeling capabilities. In order to address the above two challenges, Firstly, we introduce supervised contrastive loss to enhance the intra-class aggregation and inter-class estrangement, which is to deeply explore label information and improve the effectiveness of downstream classification tasks. Secondly, for unlabeled data, we introduce a pseudo-label-guided consistency mechanism to induce the classification results coherent across clients, which allows the representations learned by local networks to absorb the knowledge from other clients, and alleviates the disagreement between different clients for classification tasks. We conduct sufficient experiments on four commonly used datasets, and the experimental results demonstrate that our method is superior to the state-of-the-art methods, especially in the low-label rate scenario, and the improvement becomes more significant.

Medical education and artificial intelligence: Question answering for medical questions based on intelligent interaction

SummaryComputer assisted medical diagnosis technology is widely used in the field of medical assistance to assist doctors in making diagnostic decisions. But as the number of patients increases, the diagnostic pressure on doctors gradually increases, and more efficient computer‐aided medical diagnosis technology is needed to improve the accuracy of doctors' diagnosis. Today's computer‐based medically assisted diagnostic technologies suffer from the inability to fully simulate physical attributes and environmental factors, the large computational resources required for high‐precision models, the need for professional training for user operation, and the limited intuition for innovative design. For improving diagnostic efficiency, this study designs a medical Question answering intelligent interaction system in view of artificial intelligence algorithms. The system is constructed with an active interactive intelligent Q&A model consisting of a medical reasoning module and a medical examination recommendation module. Then, it uses local Bayesian network algorithm as the foundation to establish an intelligent strategy optimization network. And it puts forward the answer selection model of medical Question answering in view of hierarchical interaction for natural language processing tasks in the medical context. The performance test results show that when the diagnostic end threshold of the medical reasoning module is 0.8, the shortest diagnostic path is 3.33. When the diagnostic threshold is 0.85, the maximum length of the diagnostic path is 4.66, and the maximum difference between the diagnostic paths is 1.33, which is basically not affected by the diagnostic end threshold. The local Bayesian network algorithm can reduce the impact of noise features and extract more valuable information. The accuracy of the multilevel interactive answer selection model on the Stanford Natural Language Inference dataset without using external resources reached 89.2%. The ablation test results show that the overall accuracy of the model is 89.64%. The visualization results of the attention weight distribution test between interaction layers show that under different levels of interaction, the attention distribution will undergo significant changes.

More Than an Intermediary: James Bannerman and Colonial Space-Making on the Nineteenth-Century Gold Coast

Abstract Scholars have emphasized the importance and autonomy of African intermediaries in European imperial projects. However, intermediaries have not been studied as founders of (proto) colonial administrations. Between 1840 and 1874, the inchoate British establishment on the Gold Coast was largely a project of Anglo-African merchants, rooted in their political visions of “progress.” Merchants like James Bannerman provided infrastructure, institutions, and material form to the administration and intended it as a force for development. Ultimately, the British administration exercised its hegemony through Euro-African infrastructures, spaces, and ideas. Consequently, merchants like Bannerman undermined their local networks, rulers, and dependents who opposed British domination.

Cascaded cross-attention transformers and convolutional neural networks for multi-organ segmentation in male pelvic computed tomography.

Segmentation of the prostate and surrounding organs at risk from computed tomography is required for radiation therapy treatment planning. We propose an automatic two-step deep learning-based segmentation pipeline that consists of an initial multi-organ segmentation network for organ localization followed by organ-specific fine segmentation. Initial segmentation of all target organs is performed using a hybrid convolutional-transformer model, axial cross-attention UNet. The output from this model allows for region of interest computation and is used to crop tightly around individual organs for organ-specific fine segmentation. Information from this network is also propagated to the fine segmentation stage through an image enhancement module, highlighting regions of interest in the original image that might be difficult to segment. Organ-specific fine segmentation is performed on these cropped and enhanced images to produce the final output segmentation. We apply the proposed approach to segment the prostate, bladder, rectum, seminal vesicles, and femoral heads from male pelvic computed tomography (CT). When tested on a held-out test set of 30 images, our two-step pipeline outperformed other deep learning-based multi-organ segmentation algorithms, achieving average dice similarity coefficient (DSC) of (prostate), (bladder), (rectum), (seminal vesicles), and (femoral heads). Our results demonstrate that a two-step segmentation pipeline with initial multi-organ segmentation and additional fine segmentation can delineate male pelvic CT organs well. The utility of this additional layer of fine segmentation is most noticeable in challenging cases, as our two-step pipeline produces noticeably more accurate and less erroneous results compared to other state-of-the-art methods on such images.

Data Synchronization for Distributed Heterogeneous Database

Heterogeneous distributed database concurrent data is one of the important topics of heterogeneous databases that have important meaning. This paper discusses the mechanism of optimizing data synchronization for distributed heterogeneous database and trying to propose real solutions. Database synchronization is the exchange of records in databases on the condition that they are different. When modifications are made to a specific database, they will be applied to the database that has been synchronized in different environments and servers horizontally. The synchronization is either a one-way or two-way application and can be incidental, i.e. it is synchronous to the local network and asynchronous to the Internet due to its lagging technology. Heterogeneous distributed database systems consisting of a row storage database and a column storage database will face many difficulties, due to the inconsistent storage type such as: synchronization speed mismatch in data synchronization compared to a homogeneously distributed database system. Heterogeneous database management systems work on exchanging information for a package of various formats, accessing modification information in a heterogeneous database, maintaining the independence of the proposed system, and ensuring a good application of the proposed system in order to reach data synchronization between several packages of databases.

Analysis of hippocampal local field potentials by diffusion mapped delay coordinates

Spatial navigation through novel spaces and to known goal locations recruits multiple integrated structures in the mammalian brain. Within this extended network, the hippocampus enables formation and retrieval of cognitive spatial maps and contributes to decision making at choice points. Exploration and navigation to known goal locations produce synchronous activity of hippocampal neurons resulting in rhythmic oscillation events in local networks. Power of specific oscillatory frequencies and numbers of these events recorded in local field potentials correlate with distinct cognitive aspects of spatial navigation. Typically, oscillatory power in brain circuits is analyzed with Fourier transforms or short-time Fourier methods, which involve assumptions about the signal that are likely not true and fail to succinctly capture potentially informative features. To avoid such assumptions, we applied a method that combines manifold discovery techniques with dynamical systems theory, namely diffusion maps and Takens’ time-delay embedding theory, that avoids limitations seen in traditional methods. This method, called diffusion mapped delay coordinates (DMDC), when applied to hippocampal signals recorded from juvenile rats freely navigating a Y-maze, replicates some outcomes seen with standard approaches and identifies age differences in dynamic states that traditional analyses are unable to detect. Thus, DMDC may serve as a suitable complement to more traditional analyses of LFPs recorded from behaving subjects that may enhance information yield.

Between the lines: Life cycle impact assessment models of collision and electrocution impacts of power lines on bird diversity in Norway

AbstractThe expansion of the electric grid is inevitable. Renewable energy is on the rise, and new transmission lines must be built to link new electricity production facilities with the local network. In addition, higher electricity demand due to electrification will lead to the growth of the distribution grid. However, further construction of power lines will affect the local biodiversity. Birds are especially vulnerable: every year, power lines cause the deaths of hundreds of millions of birds by collision and electrocution. Yet the environmental impacts of the electric grid in life cycle assessment (LCA) are limited to a few impact categories, failing to cover the area of protection for damages to ecosystem quality. We developed the first methodology to quantify power lines' collision and electrocution impacts on bird richness within LCA. We calculated the potentially disappeared fraction of species (PDF) by developing species–area relationships using high‐resolution species distribution maps, species‐specific characteristics, and the location of power lines and pylons. We applied our models to Norway, a country that aims to become a low‐emission nation by 2050. The characterization factors ranged between 8.48 × 10−16 and 5.6 × 10−15 PDF*yr/kWh for collision and 3.27 × 10−18 and 1.66 × 10−16 PDF*yr/kWh for electrocution. Integrating power lines’ impacts on biodiversity in LCA is essential, as harmonized models can estimate the effects of electricity production alongside the impacts of electricity distribution. This brings us a step further in promoting a holistic assessment of energy systems.

FedCGS: Leverage Feature Compression and Conditional GAN for Privacy Protection and Efficient Communication in Federated Learning

Federated learning is a distributed machine learning technique that can train models from decentralized data, collaboratively building central models and protecting data privacy by passing partial model updates rather than raw data in each iteration of model learning. However, recent work has shown that the information during the exchange between the server and the client is still vulnerable to gradient-based privacy attacks, and traditional privacy protection methods can incur significant costs (such as communication consumption and performance evaluation). Therefore, we need an algorithm that can protect data privacy while reducing communication costs and performance losses. Here, we propose a federated learning framework FedCGS that leverages conditional generation adversarial networks and feature compression in order to achieve privacy protection while maintaining competitive model performance and effectively improving communication efficiency. We divided the local network of each client into feature extractor and public classifier, and kept the extractor local to protect privacy, and sent classifier and client generator to the server for aggregation and update through singular value decomposition, so as to improve the performance of the local network and efficient communication. A lot of experimental data prove that FedCGS can improve the performance of local model better than traditional federation learning, and improve the communication efficiency better than common conditional generation adversarial network. Therefore, we believe that FedCGS has better federal learning potential

Node2Vec and Machine Learning: A Powerful Duo for Link Prediction in Social Network

Link prediction in social networks is a challenging task that attempts to uncover hidden linkages and forecast future connections. The link prediction problem is addressed in this research article by utilizing the capabilities of Node2Vec and machine learning algorithms. To learn high-dimensional node representations that capture both local and global network structures, the Node2Vec technique is used. Then, in order to forecast potential connections, these node embedding’s are put into various machine learning models. Two real-world social network datasets are used to test the suggested methodology, and the findings show a considerable improvement in link prediction accuracy. It achieves a deeper comprehension of the hidden relationships in social networks by fusing the semantic richness of Node2Vec embedding’s with the predictive powers of machine learning methods. The results of this study extend link prediction approaches in social networks by revealing hidden ties and providing insightful predictions for upcoming connections. The suggested method indicates the potential for real-world applications in a number of fields, including recommender systems, targeted advertising, and social influence studies.

A hardware-in-the-loop (HIL) testbed for cyber-physical energy systems in smart commercial buildings

In recent years, there has been a growing trend toward the development of smart buildings that rely on cyber-physical systems (CPS) to optimize occupant comfort, safety, and energy efficiency. To ensure the reliable and efficient operation of CPS with designed control strategies, it is important to evaluate their performance under various scenarios before deploying them in the real world. This is where a Hardware-in-the-loop (HIL) testbed designed for studying sensor and control-related studies in smart buildings can be highly valuable. With the growing threat of cyber-attacks and physical faults targeting smart buildings, it is essential to ensure the security of building operations. A HIL testbed can emulate cyber-attack and physical fault scenarios, allowing researchers to develop and test threat detection and mitigation algorithms. This enables researchers to identify potential issues and optimize the algorithms in a safe and controlled environment before they are deployed in real-world settings, reducing the risk of failures that can negatively impact occupant comfort, safety, and energy efficiency. Therefore, this paper developed a HIL testbed designed for cyber-physical energy systems (e.g. buildings automation system (BAS)) in smart commercial buildings. The HIL testbed is comprised of a real-time building and Heating, Ventilation, and Air-Conditioning (HVAC) emulator using Modelica-based dynamic models, a set of BAS controllers, and a BAS computer server. The data generation capability of the HIL testbed is demonstrated by tracking normal and faulty operating data in the BAS, as well as monitoring detailed network traffic in the local BAS network. This study further demonstrates the HIL testbed’s capability by conducting case studies on real-time physical fault and cyber-attack experiments using a Department of Energy (DOE) prototype commercial building. It is anticipated that the fully functional HIL testbed will be utilized for a variety of sensor and control-related studies, including but not limited to testing, developing, validating of different HVAC control strategies, fault detection & diagnosis, energy monitoring and analysis, cyber security study, etc.

Assessing diets of marine fauna associated with emerging zoantharian habitats in the Canary Islands

Population outbreaks of zoantharians in shallow water reefs have been observed globally, including intertidal and subtidal sites in the Canary Islands. This study investigated how zoantharians might be integrating into the local trophic network. For that purpose, we assessed the feeding patterns of common species in zoantharian-dominated habitats, focusing on finding consumers of Zoanthus pulchellus and Palythoa caribaeorum. Through DNA-barcoding and metabarcoding, the gut contents of 11 predatory species were analysed, aiming to characterize their diets and explore local species feeding on zoantharians. Analyses of diet revealed a diverse range of food items and trophic positions of some of the most common and frequent marine species in the archipelago. Furthermore, based on previous observations on the different impacts of Z. pulchellus and P. caribaeorum on shallow benthic ecosystems of the Canary Islands, a preliminary approach to identify their potential influence on feeding patterns of associated species was made. Even though DNA-metabarcoding did not detect zoantharians in the gut contents of any studied species, Sanger sequencing with zoantharian-specific primers indicated their consumption by subject species may be limited to only the crab Platypodiella picta. In addition, by focusing on some of the most common species, this study enhances our understanding of the local trophic network and provides an insight into trophic dynamics in zoantharian-dominated habitats.

School Food Policy through a Project Financing

In recent years, the scientific community has focused more on urban food policies adopted by big cities and less on the local food policies adopted by small municipalities. Furthermore, the empirical evidence on school food policy initiatives is quite fragmented, and the management of the canteen service is not directly addressed by the studies carried out. In this work, the school food policy implemented in a small municipality (Corciano in the province of Perugia, Centre Italy) of about 22,000 inhabitants, through the application of project financing with the participation of local social cooperatives is presented and discussed. This paper aims to reflect on the capability of the alternative food networks developed through the project financing mechanism to identify and implement the uses of the resources concerning the local food policy objectives and the project capacity of the network. The analysis is conducted using a methodological approach based on agricultural economics and anthropology. Results from economic data analysis, collective interviews, and participant observation show that: the financial balance of the project financing is positive but quite precarious and very sensitive to market variations, both regarding the overall demand for canteen meals, and the procurement of raw materials and workforce; the project’s organizational model through a local network not only can combine the environmental, social, and health dimensions of food, but it can also reshape the local concept of community, as well as new opportunities for the circulation of food products.

Patient-Reported Outcome Measures in Atopic Dermatitis and Chronic Urticaria Are Underused in Clinical Practice

BackgroundPatient-reported outcome measures (PROMs) are validated and standardized tools that complement physician evaluations and guide treatment decisions. PROMs are crucial for monitoring atopic dermatitis (AD) and chronic urticaria (CU) in clinical practice, but there are unmet needs and knowledge gaps regarding their use in clinical practice. ObjectiveWe investigated the global real-world use of AD and CU PROMs in allergology and dermatology clinics as well as their associated local and regional networks. MethodsAcross 72 specialized allergy and dermatology centers and their local and regional networks, 2,534 physicians in 73 countries completed a 53-item questionnaire on the use of PROMs for AD and CU. ResultsOf 2,534 physicians, 1,308 were aware of PROMs. Of these, 14% and 15% used PROMs for AD and CU, respectively. Half of physicians who use PROMs do so only “rarely” or "sometimes". AD and CU PROM usage is associated with being female, younger, and a dermatologist. POSCORAD and UAS were the most utilized PROMs for AD and CU, respectively. Monitoring disease control and activity are the main drivers of the use of PROMs. Time constraints were the primary obstacle to using PROMs, followed by the impression that patients dislike PROMs. AD and CU PROM users would like training in selecting the proper PROM. ConclusionEven though PROMs offer several benefits, their use in routine practice is suboptimal, and physicians perceive barriers to their use. It is essential to attain higher levels of PROM implementation in accordance with national and international standards.

Application of implementation science for improving the utilization of an international clinical practice guidance on familial hypercholesterolemia

BACKGROUNDThe International Atherosclerosis Society (IAS) published an evidence-informed guidance for familial hypercholesterolemia (FH) that provides both clinical and implementation recommendations. We reference examples of strategies from the literature to explore how these implementation recommendations can be tailored into implementation strategies at the local-level for stakeholders guided by a framework proposed by Sarkies and Jones. METHODSFour authors of the IAS guidance selected two published exemplar implementation recommendations for detection, management, and general implementation. Each recommendation was described as an implementation strategy using Proctor's guidance for specifying and reporting implementation strategies. It recommends reporting the actor (who), action (what), action-target (who is impacted), temporality (how often), and dose (how much) for each implementation strategy. RESULTSDetection: A centralized cascade testing model, mobilized nurses (actor) to relative's homes, after the diagnosis of the proband (temporality), once (dose) to consent, obtain a blood sample and health information (action) on relatives (action-target). Management: A primary care initiative to improve FH management included an educational session (action) with clinicians (action-target), computer-based reminder message and message to patients to have their cholesterol screened once (dose) at a visit or outreach (temporality) by researchers (actor). General: A partnership between a statewide public pathology provider, local public hospital network, primary health network, government health ministry, and an academic university (actors) was established to implement a primary-tertiary shared care model (action) to improve the detection of FH (action-target). CONCLUSIONSWe demonstrate that implementation recommendations can be specified and reported for different local contexts with examples on monitoring, evaluation, and sustainability in practice.

Application of deep learning with bivariate models for genomic prediction of sow lifetime productivity-related traits.

Pig breeders cannot obtain phenotypic information at the time of selection for sow lifetime productivity (SLP). They would benefit from obtaining genetic information of candidate sows. Genomic data interpreted using deep learning (DL) techniques could contribute to the genetic improvement of SLP to maximize farm profitability because DL models capture nonlinear genetic effects such as dominance and epistasis more efficiently than conventional genomic prediction methods based on linear models. This study aimed to investigate the usefulness of DL for the genomic prediction of two SLP-related traits; lifetime number of litters (LNL) and lifetime pig production (LPP). Two bivariate DL models, convolutional neural network (CNN) and local convolutional neural network (LCNN), were compared with conventional bivariate linear models (i.e., genomic best linear unbiased prediction, Bayesian ridge regression, Bayes A, and Bayes B). Phenotype and pedigree data were collected from 40,011 sows that had husbandry records. Among these, 3,652 pigs were genotyped using the PorcineSNP60K BeadChip. The best predictive correlation for LNL was obtained with CNN (0.28), followed by LCNN (0.26) and conventional linear models (approximately 0.21). For LPP, the best predictive correlation was also obtained with CNN (0.29), followed by LCNN (0.27) and conventional linear models (approximately 0.25). A similar trend was observed with the mean squared error of prediction for the SLP traits. This study provides an example of a CNN that can outperform against the linear model-based genomic prediction approaches when the nonlinear interaction components are important because LNL and LPP exhibited strong epistatic interaction components. Additionally, our results suggest that applying bivariate DL models could also contribute to the prediction accuracy by utilizing the genetic correlation between LNL and LPP.

An Efficient Optimization Method for Antenna Arrays Using a Small Population Diploid Genetic Algorithm Based on Local RBF Networks

An Efficient Optimization Method for Antenna Arrays Using a Small Population Diploid Genetic Algorithm Based on Local RBF Networks

Turbulence Closure With Small, Local Neural Networks: Forced Two‐Dimensional and β‐Plane Flows

AbstractWe parameterize sub‐grid scale (SGS) fluxes in sinusoidally forced two‐dimensional turbulence on the β‐plane at high Reynolds numbers (Re ∼25,000) using simple 2‐layer convolutional neural networks (CNN) having only O(1000) parameters, two orders of magnitude smaller than recent studies employing deeper CNNs with 8–10 layers; we obtain stable, accurate, and long‐term online or a posteriori solutions at 16× downscaling factors. Our methodology significantly improves training efficiency and speed of online large eddy simulations runs, while offering insights into the physics of closure in such turbulent flows. Our approach benefits from extensive hyperparameter searching in learning rate and weight decay coefficient space, as well as the use of cyclical learning rate annealing, which leads to more robust and accurate online solutions compared to fixed learning rates. Our CNNs use either the coarse velocity or the vorticity and strain fields as inputs, and output the two components of the deviatoric stress tensor, Sd. We minimize a loss between the SGS vorticity flux divergence (computed from the high‐resolution solver) and that obtained from the CNN‐modeled Sd, without requiring energy or enstrophy preserving constraints. The success of shallow CNNs in accurately parameterizing this class of turbulent flows implies that the SGS stresses have a weak non‐local dependence on coarse fields; it also aligns with our physical conception that small‐scales are locally controlled by larger scales such as vortices and their strained filaments. Furthermore, 2‐layer CNN‐parameterizations are more likely to be interpretable.

Prospects of crambe for the bioeconomy of the Swabian Alb in Southwest Germany

Crambe (Crambe abyssinica Hochst. ex R.E.Fr.) is a drought-tolerant, non-edible annual crop with low fertilization needs, and there are compelling opportunities for crambe to capitalize on market growth in natural cosmetics and the regional sustainability. It is therefore proposed for cleaner biomass production on marginal land, and the development of novel value chains in rural areas. Therefore, this study assesses the prospects for growing and processing crambe in the Swabian Alb, a rural area in southwestern Germany large parts of which are characterized by marginal shallow stony soil. A literature review, stakeholder questionnaires, and a SWOT analysis were used to assess crambe’s potential in the region. This informed a locally adapted value web, which combines multiple value chains and stakeholders into one interlinked diagram showing present potential valorization opportunities for crambe in the region. However, it was found that it is not currently possible to implement a value web for crambe in the Swabian Alb. Instead, a single value chain involving farmers, cosmetics companies, and biogas plants is possible. To expand this value chain opportunity into a value web, more information is needed for all stakeholders. European Innovation Action projects could help providing more information about crambe cultivation, and to ensure ecologic and social sustainability. Economic sustainability, however, will require the involvement of other stakeholders in the value web, so that supply matches demand. Local institutions and networks can share knowledge to grow the currently possible value chain into a broader value web. This approach could also be used in other regions to assess sustainability for novel biobased value chains across social, economic, and environmental dimensions.