Biofertilizer, an environment-friendly and renewable plant nutrient source, has been widely applied and studied to reduce dependency on chemical fertilizers. However, most studies focus on the effects of biofertilizer on the bacterial and fungal communities, and we still lack an understanding of biofertilizer on the protistan community. Here, the effects of biofertilizer application on the composition and interaction of the protistan community in the wheat rhizosphere were investigated based on a 4-year field experiment. Biofertilizer application altered soil physicochemical properties and the protistan community composition (ANOSIM, p < 0.001), and significantly induced an alpha diversity decline. Random forecast and redundancy analysis demonstrated that nitrogenase activity and available phosphorus were the main drivers. Trichomonas classified to the phylum Metamonada was enriched by biofertilizer, and was significantly positive connections with soil nitrogenase activity and some function genes involved in nitrogen-fixation and nitrogen-dissimilation. Biofertilization loosely connected biotic interactions, while did not affect the stability of the protistan community. Besides, biofertilizer promoted the connections of protists with fungi, bacteria, and archaea. Combined with the conjunct biotic network (protist, fungi, bacteria, and archaea) and interactions between protists and soil physicochemical properties/function genes, protists may act as keystone taxa potentially driving soil microbiome composition and function.

Mental stress is one of the serious factors that lead to many health problems. Scientists and physicians have developed various tools to assess the level of mental stress in its early stages. Several neuroimaging tools have been proposed in the literature to assess mental stress in the workplace. Electroencephalogram (EEG) signal is one important candidate because it contain rich information about mental states and condition. In this paper, we review the existing EEG signal analysis methods on the assessment of mental stress. The review highlights the critical differences between the research findings and argues that variations of the data analysis methods contribute to several contradictory results. The variations in results could be due to various factors including lack of standardized protocol, the brain region of interest, stressor type, experiment duration, proper EEG processing, feature extraction mechanism, and type of classifier. Therefore, the significant part related to mental stress recognition is choosing the most appropriate features. In particular, a complex and diverse range of EEG features, including time-varying, functional, and dynamic brain connections, requires integration of various methods to understand their associations with mental stress. Over this, the review suggests fusing the cortical activations with the connectivity network measures and deep learning approaches to improve the accuracy of mental stress level assessment.

Abstract: As innovative way to express grief, social media posts about the deceased have become fairly common. However, few studies examined grief photos commonly posted. The purpose of the present study was to examine such pictures, as well as the motivation and reactions of those who posted, among Italians and Americans. Surveys were sent to both Italian and U.S. participants. The U.S. group yielded 262 responses (Mean age = 22 years; 81% female), the Italian yielded 51 (Mean age = 32. Several key issues emerged, such as the need to receive empathic support from other users, the desire to maintain continuing bonds, the wish to remember the deceased, and the desire to share beauty and symbolic pictures. The images were analyzed using content analysis. Both samples posted photos to remember and to enhance their posts. A strong preference for pictures with a positive emotional connotation appeared, depicting the deceased in a conjoint appearance with the participant. Results suggest that imagery used for the expression of grief in social media sites, an “iconography of grief,” is a popular means of expression for grievers.

The present study aims to analyze scientific production about technological cooperation networks in biotechnology sector, based on bibliometrics network analysis. We used the Gephi software to identify groups of partnerships, proving that the cooperation relationship is a practice used, re-sulting technological development. Findings identify that in the path for new resources that com-plement skills and competences universities are an important player in this cooperative ecosystem, and The United States is a large hub, with an extensive network of global cooperation. A strong role of its researchers in the publication of scientific articles in cooperation is highlighted. This study contributes to the advancement of the discussion about cooperative networks, as well as to the development of policies aimed at the biotechnology sector advancements

The clinical interaction between stroke and periodontitis has been consistently studied and confirmed. Hence, forecasting potentially new protein interactions in this association using bioinformatic strategies presents potential interest. In this exploratory study, we conducted a protein-protein network interaction (PPI) search with documented encoded proteins for both stroke and periodontitis. Genes of interest were collected via GWAS database. The STRING database was used to predict the PPI networks, first in a sensitivity purpose (confidence cut-off of 0.7), and then with a highest confidence cut-off (0.9). Genes over-representation was inspected in the final network. As a result, we foresee a prospective protein network of interaction between stroke and periodontitis. Inflammation, pro-coagulant/pro-thrombotic state and ultimately atheroma plaque rupture is the main biological mechanism derived from the network. These pilot results may pave the way to future molecular and therapeutic studies to further comprehend the mechanisms between these two conditions.

In daily travel and activities, pathfinding is a significant process. They are often used in transportation routes calculation. They have now evolved to be able to solve most situations of the pathfinding and its related problems. This review describes previous and recent studies on the pathfinding algorithms. It reviews the development of pathfinding algorithms in a classification base on their usage. The aim is to summarize the application of the pathfinding algorithms for the readers interested in the subject that can be used as a supplement.

In tracking-by-detection paradigm for multi-target tracking, target association is modeled as an optimization problem that is usually solved through network flow formulation. In this paper, we proposed combinatorial optimization formulation and used a bipartite graph matching for associating the targets in the consecutive frames. Usually, the target of interest is represented in a bounding box and track the whole box as a single entity. However, in the case of humans, the body goes through complex articulation and occlusion that severely deteriorate the tracking performance. To partially tackle the problem of occlusion, we argue that tracking the rigid body organ could lead to better tracking performance compared to the whole body tracking. Based on this assumption, we generated the target hypothesis of only the spatial locations of person’s heads in every frame. After the localization of head location, a constant velocity motion model is used for the temporal evolution of the targets in the visual scene. Qualitative results are evaluated on four challenging video surveillance dataset and promising results has been achieved.

Lung cancer predominates in cancer-related deaths worldwide, with lung adenocarcinoma (LUAD) being a common histological subtype of lung cancer. The aim at this study was to search for biomarkers associated with the progression and prognosis of LUAD. We have integrated the expression profiles of 1174 lung cancer patients from five GEO datasets (GSE18842, GSE19804, GSE30219, GSE40791 and GSE68465) and identified a set of differentially expressed genes. Functional enrichment analysis showed that these genes are closely related to the progression of LUAD, such as cell cycle, mitosis and adhesion. Cytoscape software was used to establish a protein-protein interaction (PPI) network to analyze important modules using Molecular Complex Detection (MCODE), and finally CCNB1, BUB1B and TTK were selected for further study. The study found that compared with non-tumor lung tissue, CCNB1, BUB1B and TTK are highly expressed in LUAD. Kaplan-Meier analysis showed that CCNB1, BUB1B and TTK were negatively correlated with the overall survival and disease-free survival of patients. Gene set enrichment analysis (GSEA) demonstrated that for the samples of any hub gene highly expressed, most of the functional gene sets enriched in cell cycle. In summary, CCNB1, BUB1B and TTK can be used as biomarkers of poor prognosis of LUAD. The high expression of CCNB1, BUB1B and TTK can accelerate the progression of LUAD and lead to shorter survival, suggesting that they may be potential targets for treatment in LUAD.

This article describes a simple Susceptible Infected Recovered (SIR) model fitting with COVID-19 data for the month of march 2020 in New York (NY) state. The model is a classical SIR, but is non-autonomous; the rate of susceptible people becoming infected is adjusted over time in order to fit the available data. The death rate is also secondarily adjusted. Our fitting is made under the assumption that due to limiting number of tests, a large part of the infected population has not been tested positive. In the last part, we extend the model to take into account the daily fluxes between New Jersey (NJ) and NY states and fit the data for both states. Our simple model fits the available data, and illustrates typical dynamics of the disease: exponential increase, apex and decrease. The model highlights a decrease in the transmission rate over the period which gives a quantitative illustration about how lockdown policies reduce the spread of the pandemic. The coupled model with NY and NJ states shows a wave in NJ following the NY wave, illustrating the mechanism of spread from one attractive hot spot to its neighbor.

Since the Coronavirus disease (COVID-19) outbreak at the end of 2019, the past two month has seen an acceleration both in and outside China in the R&D of the diagnostics, vaccines and therapeutics for this novel coronavirus. As one of the molecular forces that determine protein structure, electrostatic effects dominate many aspects of protein behaviour and biological function. Thus, incorporating currently available experimental structures related to COVID-19, this article reports a simple python-based analysis tool and a LaTeX-based editing tool to extract and summarize the electrostatic features from experimentally determined structures, to strengthen our understanding of COVID-19's structure and function and to facilitate machine-learning and structure-based computational design of its neutralizing antibodies and/or small molecule(s) as potential therapeutic candidates. Finally, this article puts forward a brief update of the structurally observed electrostatic features of the COVID-19 coronavirus.

World Health Organization (WHO) provides the guideline for managing the Particulate Matter (PM) level because when the PM level is higher, it threats the human health. For managing PM level, the procedure for measuring PM value is needed firstly. We use Tapered Element Oscillating Microbalance (TEOM)-based PM measuring sensors because it shows higher cost-effectiveness than Beta Attenuation Monitor (BAM)-based sensor. However, TEOM-based sensor has higher probability of malfunctioning than BAM-based sensor. In this paper, we call the overall malfunction as an anomaly, and we aim to detect anomalies for the maintenance of PM measuring sensors. We propose a novel architecture for solving the above aim that named as Hypothesis Pruning Generative Adversarial Network (HP-GAN). We experimentally compare the several anomaly detection architectures to certify ours performing better.

This paper introduces a fusion convolutional architecture for efficient learning of spatio-temporal features in video action recognition. Unlike 2D CNNs, 3D CNNs can be applied directly on consecutive frames to extract spatio-temporal features. The aim of this work is to fuse the convolution layers from 2D and 3D CNNs to allow temporal encoding with fewer parameters than 3D CNNs. We adopt transfer learning from pre-trained 2D CNNs for spatial extraction, followed by temporal encoding, before connecting to 3D convolution layers at the top of the architecture. We construct our fusion architecture, semi-CNN, based on three popular models: VGG-16, ResNets and DenseNets, and compare the performance with their corresponding 3D models. Our empirical results evaluated on the action recognition dataset UCF-101 demonstrate that our fusion of 1D, 2D and 3D convolutions outperforms its 3D model of the same depth, with fewer parameters and reduces overfitting. Our semi-CNN architecture achieved an average of 16 – 30% boost in the top-1 accuracy when evaluated on an input video of 16 frames.

Rocas Atoll is a unique environment in the Equatorial Atlantic Ocean, hosting a large number of endemic species and studies on the chemical diversity emerging from this biota are rather scarce. Therefore, the present work aims to assess the metabolomic diversity and pharmacological potential of the microbiota from Rocas Atoll. A total of 76 bacteria were isolated and cultured in liquid culture media to obtain crude extracts. About one third (34%) of these extracts were considered cytotoxic against human colon adenocarcinoma HCT-116 cell line. 16S rRNA gene sequencing analysis revealed that the bacteria producing cytotoxic extracts are mainly from the Actinobacteria phylum, including Streptomyces, Salinispora, Nocardiopsis and Brevibacterium genera, and in a smaller proportion from Firmicutes phylum (Bacillus). The search in the GNPS spectral library unveiled a high chemodiversity being produced by these bacteria, including rifamycins, antimycins, desferrioxamines, ferrioxamines, surfactins, surugamides, staurosporine and saliniketals, along with several unidentified compounds. Using an original approach, molecular network successfully highlighted groups of compounds responsible for the cytotoxicity of crude extracts. DEREPLICATOR+, a recently developed in silico tool (GNPS), allowed the identification of derivatives of the macrolide novonestimycin, as the cytotoxic compounds into the extracts produced by Streptomyces BRB-298 and BRB-302. Overall, these results highlighted the pharmacological potential of bacteria from this singular Atoll.

The Zika virus (ZIKV) is a mosquito-borne Flavivirus and can be transmitted through an infected mosquito bite or through human-to-human interaction by sexual activity, blood transfusion, breastfeeding or perinatal exposure. After the 2015-2016 outbreak in Brazil, a strong link between ZIKV infection and microcephaly emerged. ZIKV specifically targets human neural progenitor cells, suggesting that proteins encoded by ZIKV bind and inactivate host cell proteins leading to microcephaly. Here, we present a systematic annotation of interactions between human proteins and the seven non-structural ZIKV proteins corresponding to a Brazilian isolate. The interaction network was generated by combining tandem-affinity purification followed by mass spectrometry with yeast two-hybrid screens. We identified 150 human proteins, involved in distinct biological processes, as interactors to ZIKV non-structural proteins. Our interacting network is composed of proteins that have been previously associated with microcephaly in human genetic disorders and/or animal models. This study builds on previously published interacting networks of ZIKV and genes related to autosomal recessive primary microcephaly to generate a catalog of human cellular targets of ZIKV proteins implicated in processes related to microcephaly in humans. Collectively, this data can be used as a resource for future characterization of ZIKV infection biology and help create a basis for the discovery of drugs which may disrupt the interaction and reduce the health damage to the fetus.

Alzheimer's disease (AD) and Parkinson's disease (PD) are the most common neurodegenerative disorders related to aging. Though several risk factors are shared between these two diseases, the exact relationship between these two diseases is still unknown. In this paper, we analyzed how these diseases relate to each other from a genomics viewpoint. Using an extensive literature search, we accumulated the list of genes from the major genome-wide association (GWAS) studies. However, we found only one gene (HLA-DRB5) reported in these GWAS studies that are common between AD and PD. We also listed all the miRNAs that have been previously reported for AD and PD. Here we found 15 different miRNAs that were reported in both diseases. In order to get better insights, we predicted the gene coexpression network for both AD and PD. Network analysis on these networks show six clusters of genes related to AD and four clusters of genes related to PD.

We present a non-linear non-homogeneous fitness-complexity algorithm where the presence of non homogeneous terms guarantees both convergence and stability. After a suitable rescaling of the relevant quantities, the non homogeneous terms are eventually set to zero so that this new method is parameter free. This new algorithm reproduces the findings of the original algorithm proposed by Tacchella et al. [1], and allows for an approximate analytic solution in case of actual binarized RCA matrices. This solution discloses a deep connection with the network theory of bipartite graphs. We define the new quantity of “country net-efficiency” quantifying how a country efficiently invests in capabilities able to generate innovative high quality products. Eventually, we demonstrate analytically the local convergence of the algorithm.

A The agri-food sector is in full renovation, continuously demanding new systems that allow farmers to facilitate their work. Efficient agricultural practices are essential for increasing farm profitability. Efficient agricultural practices can be increased by understanding and managing water neeeds. However, real-time monitoring of water needs is currently slow, and irrigation decisions are based on previous data or physical evidence. Furthermore, the prices of automatic systems for collecting data from several sources (soil and climate) are expensive and the autonomy is very low. Emerging Internet of Things (IoT) technologies such as wireless sensor networks can be used to collect vast amounts of data recorded via apps. By means of an LPWAN communication the farmer can know in real time the state of his crops thanks to a large number of sensors connected wirelessly and distributed across his farm. This paper presents a low consumption solution based on LoRaWAN technology. The wireless sensor node, called BoX, exhibits very low power since it has been optimized both in terms of hardware and software. The result is a higher degree of autonomy than commercial motes. That will allow the farmer to have all the information necessary to achieve an efficient management of his crops with full autonomy.

In mega cities such as Seoul in South Korea, it is very important to protect the city from the flooding even for the short time of period due to the enormous amount of economic damage. In impervious area of the city, stormwater pipe network is commonly applied to discharge rainfall to the outside of catchment. Therefore, the stormwater pipe network in urban catchment should be carefully designed to discharge the runoff quickly and efficiently. In this study, different types of structures in stormwater pipe network were evaluated using the relationship between the peaks rainfall and runoff in urban catchments in South Korea. More than 400 historical rainfall events were applied in five urban catchments to estimate peak runoff from different type of network structures. Linear regression analysis was implemented to estimate peak runoffs. The coefficient of determination of the regressions were higher than 0.9 which means the regression model represent very well the relationship between the two peaks. However, the variation of the prediction becomes large as the peak rainfall increases and the variation become even larger when the network structure is branched. Therefore, it depends on the structure of stormwater pipe network. When the water paths in the pipe network is unique (branched network), the increased amount of rainfall is congested around the rainwater inlets and the uncertainty of peak runoff prediction is increased. If there are many possible water paths depending on the amount of discharge (looped network), the increased rainfall is discharged more quickly through the many water paths. This can be a way to represent the reliability of the stormwater pipe network. The structures of stormwater pipe network is evaluated using drainage density which is the length of pipes over the unit catchment area and 95% confidence interval. As a result, the 95% confidence interval is increased as the drainage density is increased because the accuracy of peak runoff prediction is decreased. As mentioned earlier, because the looped networks have many alternative water flowing paths, elimination time of rainfall from the catchments become short, the 95% confidence interval become narrow, and the reliability of peak runoff prediction become high. Therefore, it is beneficial to install looped stormwater pipe network within the affordable budget. It is important factor to determine the amount of complexity in stormwater pipe network to decrease the risk of urban flooding.

The current urban environment is faced with the potential threat of frequent natural disasters, and the sustainable development of post-disaster community has become a global issue. As an intrinsic motivation influencing the social interaction and capital operation of community, social network is an important mechanism promoting such sustainable development. However, the difference in social network caused by different member structure, spatial arrangement and management mechanism of post-disaster communities in different reconstruction modes has influenced such sustainable development process. Therefore, reasonable selection of reconstruction mode is crucial. This paper applied analytic hierarchy process to comprehensively measure and compare the social network strength in post-disaster communities in the four reconstruction modes adopted by the government of China, i.e. unified planning and unified construction, unified planning and independent construction, in situ reconstruction and relocation resettlement, with communities after the 2008 Sichuan earthquake in Chengdu, China as study objects from the perspective of three social relations (the relations between residents and residents, residents and managers, and residents and servers). The results showed that strong connections are generally presented in the social network of post-disaster communities in unified planning modes, that the strength is significantly higher than that of those in non-unified planning modes, and that the strength of UPIC communities is the highest. Meanwhile, government intervention, residents’ free participation and market operation are positively correlated to government trust, community interaction and community service respectively. The positive impact of government intervention is the most significant, but it has a peak value. No government management and excessive government intervention will exert negative impacts. The coordination of government, society and market is the key contents of post-disaster community reconstruction. The reconstruction modes based on “government leadership, resident participation and market operation” may become a feasible path for such sustainable development.

Nonlinear rheological properties of chiral crystal cholesteryl oleyl carbonate (COC) in blue phase III are investigated under different shear deformations; large amplitude oscillatory shear, step shear deformation, and continuous shear flow. Rheology of the liquid crystal is significantly affected by structural rearrangement of defects under shear flow. One of the examples on the defect-mediated rheology is the blue phase rheology. Blue phase is characterized by three dimensional network structure of the disclination lines. It has been numerically studied that the rheological behavior of the blue phase is dominated by destruction and creation of the disclination networks. In this study, we find that the nonlinear viscoelasticity of BPIII is characterized by the fracture of the disclination networks. Depending on the degree of the fracture, the nonlinear viscoelasticity is divided into two regimes; the weak nonlinear regime where the disclination network locally fractures but still show elastic response, and the strong nonlinear regime where the shear deformation breaks up the networks, which results in a loss of the elasticity. Continuous shear deformation reveals that a series of the fracture process delays with shear rate. The shear rate dependence suggests that force balance between the elastic force acting on the disclination lines and the viscous force determines the fracture behavior.

Accurate measurement of pedaling kinetics and kinematics is vital for optimizing rehabilitation, exercise training, and understanding musculoskeletal biomechanics. Pedal reaction force, the main external force in cycling, is essential for musculoskeletal modeling and closely correlates with lower limb muscle activity and joint reaction forces. However, sensor instrumentation like 3-axis pedal force sensors is costly and requires extensive post-processing. Recent advancements in machine learning (ML), particularly neural network (NN) models, provide promising solutions for kinetic analyses. In this study, an NN model was developed to predict radial and mediolateral forces, providing a low-cost solution to study pedaling biomechanics with stationary cycling ergometers. Fifteen healthy individuals performed a 2-minute pedaling task at two different self-selected (58±5 rpm) and higher (72±7 rpm) cadences. Pedal forces were recorded using a 3-axis force system. The dataset included pedal force, crank angle, cadence, power, and participants' weight and height. The NN model achieved an inter-subject normalized root mean square error (nRMSE) of 0.15±0.02 and 0.26±0.05 for radial and mediolateral forces at high cadence, respectively, and 0.20±0.04 and 0.22±0.04 at self-selected cadence. The NN model's low computational time suits real-time pedal force predictions, matching the accuracy of previous ML algorithms for estimating ground reaction forces in gait.

The metaverse is gradually expanding. There is a growing number of photo and video recordings of metaverse virtual worlds being used in multiple domains, with growing collections. An essential element of the metaverse and its recordings are avatars. In this paper, we present a novel task of avatar detection in metaverse recordings, supporting semantic retrieval in collections of metaverse recordings and other use cases. Our work addresses the characterizations and definitions of avatars and presents a new model supporting avatar detection. The latest object detection algorithms are trained and tested on a variety of avatar types in metaverse recordings. Our work achieves a higher level of accuracy than existing models, which encourages further research in this field.

The use of artificial intelligence algorithms (AI) has gained importance for dental applications in recent years. Analyzing using IA information from different sensor data such as images or X-ray radiographs can help to improve medical decisions and to achieve early diagnosis of different dental pathologies. In particular, the use of deep learning (DL) techniques based on convolutional neural networks (CNNs) has obtained promising results in dental applications based on images, in which approaches based on classification, detection, and segmentation are being studied with growing interest. However, there are still several challenges to be tackled, such as the data quality and quantity, the variability among categories, and the analysis of the possible bias and variance associated with each dataset distribution. In this work, we compare three different DL object detection models, which are Faster R-CNN, YOLO V2, and SSD. Each object detection architecture was trained, calibrated, validated, and tested with three different feature extraction CNNs which are ResNet-18, ResNet-50, and ResNet-101, which were the networks that best fit our dataset distribution. Based on such detection networks, we detect four different categories of angles in third molars using X-ray panoramic radiographs by using Winter's classification criterion. This criterion characterizes the third molar's position regarding the second molar's longitudinal axis. The detected categories for the third molars are distoangular, vertical, mesioangular, and horizontal. For training, we used a total of 644 panoramic X-ray images. The results obtained in the testing dataset reached up to 99% mean average accuracy performance, demonstrating the YOLOV2 obtained higher effectiveness in solving the third molar angle detection problem. These results demonstrate that the use of CNNs for object detection in panoramic X-rays represents a promising solution in dental applications.

The representation of intelligence is achieved by patterns of connections among neurons in brains and machines. Brains grow continuously, such that their patterns of connections develop through activity-dependent specification with the continuing ontogenesis of individual experience. The theory of active inference proposes that the developmental organization of sentient systems reflects general processes of informatic self-evidencing, through the minimization of free energy, that may be described in information terms that are not dependent on a specific physical substrate. At a certain level of complexity, self-evidencing of living (self-organizing) information systems becomes hierarchic and reentrant, such that effective consciousness emerges as the consequence of a good regulator. These principles imply that an adequate reconstruction of the computational dynamics of an individual human brain is possible with a sufficient neuromorphic emulation.

This study optimizes the placement and farm layout of Vertical Axis Wind Turbines (VAWTs) using a neural fuzzy network, an advanced machine learning system, and meta-heuristic algorithms. The methodology introduces a novel approach to enhance turbine efficiency and overall farm performance. The objective is to determine the optimal configuration of vertical axis wind turbines using a neural-fuzzy system and meta-heuristic optimizers. Turbine efficiency and power generation rates are assessed through three-dimensional numerical simulations based on the Reynolds-averaged Navier-Stokes equations. This innovative design, featuring straight blades with bevel-angle vortex generators, represents a significant advancement over traditional straight-blade VAWTs. Comparative analyses demonstrate that the oblique configuration exhibits higher average output moment and power. A novel concept integrates the strengths of Darrieus VAWTs, enhancing efficiency through vortex generator integration. Simulation results are validated with empirical data, confirming the superior aerodynamic efficiency and increased power generation of the oblique configuration. Inspired by the optimal group movements of birds, this study recommends adopting the oblique arrangement for improved wind turbine performance.

Methotrexate is an antimetabolic agent with proliferative and immunosuppressive activity. It has been demonstrated to be an effective treatment for acute lymphoblastic leukemia (ALL) in children. However, there is evidence of an association between methotrexate and toxicity risks, which influences the personalization of treatment, particularly in the case of childhood ALL. This article presents the development and implementation of an algorithm based on artificial neural networks to detect methotrexate toxicity in pediatric patients with acute lymphoblastic leukemia. The algorithm utilizes historical clinical and laboratory data, with an effectiveness of 99% in the tests performed with the patients dataset. The use of neural networks in medicine is often linked to disease diagnosis systems. However, neural networks are not only capable of recognizing examples, but also hold very important information. For this reason, one of the main areas of application of neural networks is the interpretation of medical data. In this article we diagnose with the application of neural networks in medicine with a concrete example: Detecting Methotrexate in Pediatric Patient in its early stages.

In this article, we propose a circuit to imitate the behavior of a Reward-Modulated Spike-Timing-Dependent Plasticity synapse. When two neurons in adjacent layers produce spikes, each spike modifies the thickness of the common synapse. As a result, the synapse’s ability to conduct impulses is controlled, leading to an unsupervised learning rule. By introducing a reward signal, reinforcement learning is enabled by redirecting the growth and shrinkage of synapses based on signal feedback from the environment. The proposed synapse manages the convolution of the emitted spike signals to promote either the strengthening or weakening of the synapse, which is represented as the resistance value of a memristor device. As memristors have a conductance range that may differ from the available current input range of typical CMOS neuron designs, the synapse circuit can be adjusted to regulate the spike’s amplitude current to comply with the neuron. The circuit described in this work allows for the implementation of fully interconnected layers of neuron analog circuits. This is achieved by having each synapse reconform the spike signal, thus removing the burden of providing enough power from the neurons to each memristor. The synapse circuit was tested using a CMOS analog neuron described in the literature. Additionally, the article provides insight into how to properly describe the hysteresis behavior of the memristor in Verilog-A code. The testing and learning capabilities of the synapse circuit are demonstrated in simulation using the Skywater-130nm process. The article’s main goal is to provide the basic building blocks for Deep Neural Neural Networks relying on spiking neurons and memristors as the basic processing elements to handle spike generation, propagation, and synaptic plasticity.

Fault detection in transmission lines plays a role in maintaining the dependability and steadiness of power networks. Traditional methods for identifying faults often struggle to handle the diverse nature of real world fault situations. Machine learning (ML) algorithms offer a data centered approach that can adjust and learn from datasets potentially overcoming the limitations of traditional approaches. This document presents a review of progress in using ML for detecting faults in transmission lines. By drawing insights from a variety of studies we explore how ML algorithms have evolved in fault detection, including techniques like networks, recurrent neural networks featuring Long Short Term Memory and convolutional neural networks. We delve into the spectrum of applications where ML is used for fault detection across fault scenarios and operational settings. Additionally we discuss the obstacles and prospects linked to putting ML based fault detection systems into practice such as challenges with data quality, model interpretability and integration with existing grid monitoring systems. Lastly we outline future research paths focused on pushing forward the boundaries of fault detection, in power transmission systems through approaches and collaborative endeavors involving academia, industry players and policymakers. In general, this review highlights how machine learning has the power to revolutionize fault detection methods enhancing the resilience and dependability of power systems.

Being able to express broad families of equivariant or invariant attributed graph functions is a popular measuring stick of whether graph neural networks should be employed in practical applications. However, it is equally important to learn deep local minima of losses (i.e., with much smaller loss values than other minima), even when architectures cannot express global minima. In this work we introduce the architectural property of attracting GNN optimization trajectories to local minima as a means of achieving smaller losses. We take first steps in satisfying this property for losses defined over attributed undirected unweighted graphs with a novel architecture, called Universal Local Attractor (ULA). The latter refines each dimension of end-to-end trained node feature embeddings based on graph structure to track the optimization trajectories of losses satisfying some mild conditions. The refined dimensions are then linearly pooled to create predictions. We experiment on 10 tasks, from node classification to clique detection, on which ULA is comparable with or significantly outperforms popular alternatives of similar or greater theoretical expressive power.

Nowadays the dynamism induced by the constant change of strategic decisions on the markets produces an extra difficulty in the management of an organization. The strategic decisions made by managers can become obsolete in a short period of time. One of the major difficulties in managing a commercial organization is to predict, with some precision degree, the impact some strategic decisions have on the financial results. Business Intelligence (BI) is an area widely used to help managers to make strategic decisions. But the methods used, behind the scenes, to achieve the conclusions are kept secret by BI company-based services. Modelling the environment can be a good option to study the impact of an action, provided by a strategic decision, in a real environment. A good model should give an approximate result of an action applied to a previous state of the environment. Artificial Neural Networks (ANNs) are proven to be excellent in modeling environments with some level of data noise. The same strategic action can have different results in different organizations. A tool that allows an evaluation of a strategic action applied to an environment should have a major importance in the management scope. Modeling the environment should save time and money for the organization to improve the performance of the strategic plan. If one evaluates the state of the environment after a strategic action being applied, it can be possible to mitigate the risk of failure of the strategic plan. As we will be able to verify, it is possible to use ANNs to model strategic environments that should allow the prediction of sales and operating results by the used strategies with some precision, although the level of success will be directly related with the user’s necessity.

Accurate estimations of actual evapotranspiration (ETa) are fundamental for various environmental issues. Artificial Intelligence-based models are considered a promising alternative to the most common direct ETa estimation techniques and indirect methods by remote sensing (RS)-based surface energy balance models. Artificial Neural Networks (ANN) are proven to be suitable for predicting reference evapotranspiration and ETa based on RS data. The aim of this study is to develop a methodology based on ANNs for estimating daily ETa values using NDVI and land surface temperature, coupled with limited site-specific climatic variables at a large irrigation catchment. Two scenarios were implemented by the ANN model. Data from only the 38 days of satellite overpass dates was selected in Scenario-I, while the 769-day data included the satellite overpass dates and other days located between two satellite overpass acquisitions in Scenario-II. An irrigation scheme in the Mediterranean region of Turkiye was selected, and a total of 38 Landsat images, and local climatic data were used in 2021 and 2022. Results showed that R2 values in Scenario-I and II were acknowledgeably high for training (0.79 and 0.86), testing (0.75 and 0.81), and the entire dataset (0.76 and 0.84), respectively. Results of the new model in two scenarios showed acceptable agreement with ETa-METRIC values. The proposed ANN model demonstrated the potential of obtaining daily ETa using limited climatic data and RS imagery.

Convolutional neural networks (CNNs) have proven to be a very efficient class of machine learning (ML) architectures for handling multidimensional data by maintaining data locality, especially in the field of computer vision. Data pooling, a major component of CNNs, plays a crucial role for extracting important features of the input data and downsampling its dimensionality. Multidimensional pooling, however, is not efficiently implemented in existing ML algorithms. In particular, quantum machine learning (QML) algorithms have a tendency to ignore data locality for higher dimensions by representing/flattening multidimensional data as simple one-dimensional data. In this work, we propose using the quantum Haar transform (QHT) and quantum partial measurement for performing generalized pooling operations on multidimensional data. We present the corresponding decoherence-optimized quantum circuits for the proposed techniques along with their theoretical circuit depth analysis. Our experimental work was conducted using multidimensional data, ranging from 1-D audio data, to 2-D image data, to 3-D hyperspectral data, to demonstrate the scalability of the proposed methods. In our experiments, we utilized both noisy and noise-free quantum simulations on a state-of-the-art quantum simulator from IBM Quantum. We also show the efficiency of our proposed techniques for multidimensional data by reporting the fidelity of results.

Background: Genome-wide association studies (GWAS) have shed light on various complex diseases and traits, by detecting more than 400,000 associated genetic loci. This number is expected to drastically increase because of the use of novel artificial intelligence methods offering new ways to study the effects of variants. Deep learning using artificial neural networks (ANN) is a sub-field of artificial intelligence, which simulates how the human brain learns. We aimed at assessing the potential of deep learning in human genetic studies of Alzheimer’s Disease (AD) and how these compare to the traditional statistical methods used in GWAS, by simultaneously testing the two approaches on the same dataset, while discovering new genetic loci associated to AD. Methods: To address this aim, phenotypic and genome-wide SNP data from the UK Biobank was analysed on a binary outcome, AD diagnosis, in two different data balance options, of one-to-one and one-to-two case-control datasets, using 2,764 cases vs 2,764 controls and 5,528 controls respectively matched on gender, age, ethnicity, PC1-20 and genotyping array. Genetic data handling and GWAS were performed using PLINK, whereas neural networks were trained using GenNet, a new ANN tool, with the same datasets, separated into training (60%), validation (20%) and test (20%) sets. Neural network layers were determined using biological knowledge, by annotating SNPs to genes and genes to AD related pathways, using ANNOVAR annotations followed by GeneSCF and KEGG. Results: Significant associations were detected between four SNPs linked to two different genes and AD for the 1 to 1 case-control study design and six SNPs linked to four different genes for the 1 to 2 case-control study design by using PLINK. All identified regions have been previously associated to AD. GenNet identified twelve SNPs on seven genes to be associated with AD, all with biological plausibility, achieving an AUC of 0.80 when using three biologically determined layers and 0.73 when using two layers at the neural networks. No common top SNPs were identified between the machine learning and GWAS models. Conclusion: This is one of the first studies attempting to compare the traditional GWAS to more sophisticated state-of-art methods for understanding the genetic architecture of complex phenotypes using the same dataset. More systematic comparisons with such approaches on real data are needed to enable best practises for machine learning in the analysis of genome-wide genetic data.

The purpose of this study is to ​​explore the use of a custom Transformer model in brain-computer interfaces (BCIs) that translate the neural activity present when an individual with limited verbal and fine-motor skills attempts to handwrite. As found in previous studies, Transformers have performed better than recurrent neural networks (RNNs) in translation tasks which are similar to its usage here in decoding neural signals into intended handwritten text. Due to the known benefits of a Transformer, the hypothesis was that the Transformer would show promise in the context of a BCI through the recorded metrics. The neural signals of a tetraplegic individual, when they attempted to handwrite, were provided by existing research. Four trials were conducted using data with or without augmentation which the model used when training to separately minimize training loss and validation loss. When comparing the results of a BCI with the implementation of a Transformer model with the original RNN BCI (the original data source), the Transformer model performed less favorably across all four trials. Although the results do not indicate that the Transformer model currently outperforms an RNN BCI, it is important to note that further testing of the model's capabilities (such as training it with a larger and more preferable dataset and/or for longer, comparing training times between the RNN and Transformer, and/or seeing how the Transformer is improved with an offline autocorrect feature) is necessary before determining whether Transformers can enhance communication in this manner.

In the intricate domain of text analysis, syntactic dependency trees play a crucial role in unraveling the web of relations among entities embedded in the text. These trees provide a structural roadmap, guiding us through the complex syntax to pinpoint the interactions and connections between different entities. However, the challenge lies in sifting through this intricate structure to extract relevant information, a task that requires precision and discernment. Traditional approaches often rely on rule-based pruning methods to simplify these dependency structures, focusing on certain parts while discarding others. Yet, this approach has its pitfalls, as it can overlook critical nuances and connections that are vital for a comprehensive understanding of the text. Addressing this gap, our research introduces the Syntactic Dependency-Aware Neural Networks (SDANNs), a groundbreaking model designed to harness the full power of the entire dependency tree. This approach marks a significant departure from the conventional methods. Instead of the rigid rule-based pruning, SDANNs implement a more flexible and dynamic 'soft-pruning' technique. This method allows the model to adaptively focus on the sub-structures within the dependency tree that are most relevant for understanding the relationships between entities. By doing so, it ensures that no vital information is overlooked, and all potential connections are considered. The efficacy of SDANNs is not just theoretical but has been empirically validated through extensive testing and evaluations across a wide range of tasks. These tasks include the extraction of complex relations spanning multiple sentences, as well as detailed analyses at the sentence level. In each of these scenarios, SDANNs have demonstrated a remarkable ability to leverage the full structural complexity of dependency trees. This capability sets them apart from existing models, enabling a more nuanced and comprehensive analysis of textual relations. The results of these evaluations consistently show that SDANNs not only meet but significantly exceed the performance of prior models. This superiority is evident in the way SDANNs handle the multifaceted and often subtle interactions within the text, offering insights that were previously inaccessible with conventional methods. In summary, the Syntactic Dependency-Aware Neural Networks represent a significant advancement in the field of text analysis. By fully embracing the complexity of syntactic dependency trees and employing a sophisticated 'soft-pruning' approach, SDANNs open new avenues for exploring and understanding the intricate relationships that exist within written language. This model stands as a testament to the potential of combining advanced neural network architectures with a deep understanding of linguistic structures, paving the way for more accurate, nuanced, and comprehensive analyses of text.

Mammalian cells have evolved to function under Earth’s gravity, but how they respond to microgravity remains largely unknown. Neural stem cells (NSCs) are essential for the maintenance of central nervous system (CNS) functions during development and the regeneration of all CNS cell populations. Here, we examined the behavior of space (SPC)-flown NSCs as they readapted to Earth’s gravity. We found that most of these cells survived the space flight and self-renewed. Yet, some showed autophagy-like behaviors (ALB). To ascertain if the secretome from SPC-flown NSCs contained molecules inducing this behavior, we incubated naïve, non-starved NSCs in a medium containing SPC-NSCs secretome. We found a four-fold increase in the ALB rate. Proteomic analysis of the secretome revealed that the protein of highest content produced by SPC-NSCs was secreted protein acidic and rich in cysteine (SPARC), which triggers endoplasmic reticulum (ER) stress leading to lethal ALB. These results offer novel knowledge on the response of neural cells, particularly NSCs, subjected to space microgravity. Moreover, some secreted proteins have been identified as microgravity sensing, paving a new venue for future research aiming at targeting SPARC metabolism. Although we did not establish a direct relationship between ALB and SPARC as a potential marker, these results represent the first step in the identification of gravity sensing molecules as targets to be modulated and to design effective countermeasures to mitigate intracranial hypertension in astronauts using structure-based-protein design.

Artificial intelligence techniques are now widely used in various agricultural applications, including the detection of devastating diseases such as late blight (Phytophthora infestans) and early blight (Alternaria solani) affecting potato (Solanum Tuberorsum L.) crops. In this paper, we present a mobile application for potato crop pest detection based on deep neural networks. The images were taken from the PlantVillage dataset with a batch of 1000 images for each of the three identified classes. An exploratory analysis of the architectures used for early and late blight diagnosis in potatoes was performed, achieving an accuracy of 98.76%, with MobileNetv2. Based on the results obtained, an offline mobile application was implemented, supported on devices with Android 4.1 or later, also featuring an information section on the 27 pests affecting potato crops and a gallery of symptoms. For future work, segmentation techniques will be used to highlight the damaged region in the potato leaf by evaluating its extent and possibly identifying different types of pests affecting the same plant.

In recent years, applying deep learning to solve physics problems has attracted much attention. Data-driven deep learning methods produce operators that can learn solutions to the whole system of partial differential equations. However, the existing methods are only evaluated on simple flow equations (e.g., Burger's equation), and only consider the generalization ability on different initial conditions. In this paper, we construct CFDBench, a benchmark with four classic problems in computational fluid dynamics (CFD): lid-driven cavity flow, laminar boundary layer flow in circular tubes, dam flows through the steps, and periodic Karman vortex street. Each flow problem includes data with various boundary conditions, fluid physical properties, and domain geometries. Compared to existing datasets, the advantages of CFDBench are (1) comprehensive. It contains common physical parameters such as velocity, pressure, and cavity fraction. (2) realistic. It is very suitable for deep learning solutions of fluid mechanics equations. (3) challenging. It has a certain learning difficulty, prompting to find models with strong learning ability. (4) standardized. CFDBench facilitates a comprehensive and fair comparison of different deep learning methods for CFD. We make appropriate modifications to popular deep neural networks to apply them to CFDBench and enable the accommodation of more changing inputs. The evaluation on CFDBench reveals some new shortcomings of existing works and we propose possible directions for solving such problems.

The definition of artificial intelligence (AI) is the capacity of a computer or machine to mimic or simulate human intelligence. AI has been applied in different areas, including medicine. In cardiology, AI techniques have revolutionized the field of cardiac diagnosis, enabling the detection and prediction of cardiovascular diseases to be more accurate and efficient. This article provides an overview of machine learning, deep learning, and neural networks as they pertain to cardiac diagnosis. We will investigate how these techniques harness the power of data and algorithms to analyze complex patterns in cardiac data, thereby facilitating early detection, risk assessment, and treatment decision-making.

Deep neural networks with powerful auto-optimization tools have been widely applied in various research fields, e.g., NLP and computer vision. However, existing neural network architectures typically are constructed using different inductive biases, e.g., preconceptions, expecting to decrease parameter search space during training, reduce computational cost or introduce expert knowledge in the neural network design. As an alternative, Multilayer Perceptron (MLP) provides much better freedom for exploration, has a lower inductive bias than convolutional neural networks (CNNs), and offers good flexibility in learning complex patterns. Even though, such neural architectures are commonly built in a flat Euclidean space, which is not necessarily the optimal space for any data, and is especially not good for modeling hierarchical correlations. Hyperbolic neural networks (HNNs) have gained attention for their ability to capture hierarchical structures present in complex data types like graphs. Recently, there has been an increasing interest to extend HNNs to computer vision tasks, motivated by the observations that images possess rich hierarchical relations. However, this is generally applied by employing a Euclidean backbone for learning higher-level semantic representations and only incorporating a hyperbolic classifier for classification, which, we argue, does not make full use of the advantage of hyperbolic space. Considering the recovery of the attention-free Multilayer Perceptron(MLP), in this paper, we extend it to non-Euclidean space and propose a novel architecture, named Hyperbolic Res-MLP (HR-MLP), that leverages fully hyperbolic layers to learn feature embeddings and perform image classification in an end-to-end fashion. With the help of the proposed Lorentz cross-patch and cross-channel layers, we can directly perform operations in the hyperbolic domain with fewer parameters, making it faster to train and providing comparatively better performance than its Euclidean counterpart. Experiments on CIFAR10, CIFAR100, and MiniImageNet demonstrate a comparable and superior performance when compared to Euclidean baselines. Our code is available at (https://github.com/Ahmad-Omar-Ahsan/HR-MLP)

Symbolic semantic understanding of staff images is an important part in music information retrieval. Due to the complex composition of staff symbols and the strong semantic correlation between symbol spaces, it is difficult to understand the pitch and duration of each note during performances. In this paper, we design a semantic understanding system for optical staff symbols. The system uses the YOLOv5 to implement optical staff’s low-level semantic understanding stage, which understands the pitch and duration in natural scales and other symbols that affect the pitch and duration. The proposed note encoding reconstruction algorithm is used to implement high-level semantic understanding stage. Such algorithm understands the logical, spatial, and temporal relationships between natural scales and other symbols based on music theory, and outputs digital codes for the pitch and duration of main notes during performances. The model is trained with a self-constructed SUSN dataset. Experimental results of YOLOv5 show that the precision is 0.989 and the recall is 0.972. For the system, the error rate is 0.031 and the omission rate is 0.021. The paper concludes by analysing the causes of semantic understanding errors and offers recommendations for further research. The results of this paper provide a method for multimodal music artificial intelligence applications such as notation recognition through listening, intelligent score flipping and automatic performance.

Automatic and real-time pose estimation is important in monitoring animal behavior, health and welfare. In this paper, we utilized pose estimation for monitoring farrowing process to prevent piglet mortality and preserve the health and welfare of sow. State-of-the-art Deep Learning (DL) methods have lately been used for animal pose estimation. The aim of this paper was to probe the generalization ability of five common DL networks (ResNet50, ResNet101, MobileNet, EfficientNet and DLCRNet) for sow and piglet pose estimation. These architectures predict body parts of several piglets and the sow directly from input video sequences. Real farrowing data from a commercial farm was used for training and validation of the proposed networks. The experimental results demonstrated that MobileNet was able to detect seven body parts of the sow with median test error of 0.61 pixels.

This paper proposes an encryption scheme for high pixel density images. Based on the application of the quantum random walk algorithm, the Long short-term memory (LSTM) can effectively solve the problem of low efficiency of the quantum random walk algorithm in generating large-scale pseudorandom matrices, and further improve the statistical properties of the pseudorandom matrices required for encryption. The LSTM is then divided into columns and fed into the LSTM in order for training. Due to the randomness of the input matrix, the LSTM cannot be trained effectively, so the output matrix is predicted to be highly random. The LSTM prediction matrix of the same size as the key matrix is generated based on the pixel density of the image to be encrypted, which can effectively complete the encryption of the image. In the statistical performance test, the proposed encryption scheme achieves an average information entropy of 7.9992, an average number of pixels changed rate (NPCR) of 99.6231%, an average uniform average change intensity (UACI) of 33.6029% and an average correlation of 0.0032. Finally, various noise simulation tests are also conducted to verify its robustness in real-world applications where common noise and attack interference are encountered.

For a mobile robot, navigation in a densely crowded space can be a challenging and sometimes impossible task, especially with traditional techniques. In this paper, we present a framework to train neural controllers for differential drive mobile robots which must safely navigate a crowded environment while trying to reach a target location. To learn the robot’s policy, we train a convolutional neural network using two reinforcement learning algorithms, Deep Q-Networks (DQN) and Asynchronous Advantage Actor Critic (A3C), and develop a training pipeline that allows to scale the process to several compute nodes. We show that the asynchronous training procedure in A3C can be leveraged to quickly train neural controllers and test them on a real robot in a crowded environment.

Skin detection, the process of distinguishing between skin and non-skin regions in a digital image, is widely used in a variety of applications ranging from hand gesture analysis to body part tracking to facial recognition. Skin detection is a challenging problem that has received a lot of attention from experts and proposals from the research community in the context of intelligent systems, but the lack of common benchmarks and unified testing protocols has hampered fairness among approaches. Comparisons are very difficult. Recently, the success of deep neural networks has had a major impact on the field of image segmentation detection, resulting in various successful models to date. In this work, we survey the most recent research in this field and propose fair comparisons between approaches using several different datasets. The main contributions of this work are: (i) a comprehensive literature review of approaches to skin color detection and a comparison of approaches that may help researchers and practitioners choose the best method for their application; (ii) a comprehensive list of datasets that report ground truth for skin detection; (iii) a framework for evaluating and combining different skin detection approaches. Moreover, we proposed an ensemble of convolutional neural networks and transformers that obtains state of the art performance. All the code is made publicly available at https://github.com/LorisNanni

3D reconstruction from a single 2D input is a classic problem in the field of computer vision. With the advancements in deep learning, the performance of 3D reconstruction has also significantly improved. The reconstruction task is more difficult for objects with no textures or complex deformations. This paper serves as a review of recent literature on 3D reconstruction from a single view, with a focus on deep learning methods from 2018 to 2021. Due to lack of standard datasets or 3D shape representation methods, it is hard make direct comparisons between all reviewed methods. However, this paper reviews different approaches for reconstructing 3d shape as depth maps, surface normals, point clouds and meshes; along with various loss functions and evaluation metrics used to train and evaluate these methods.

When computers start to become a dominant part of technology around the 1950s, fundamental questions about reliable designs and robustness were of great relevance. Their development gave rise to the exploration of new questions such as what made brains reliable (since neurons can die) and how computers could get inspiration from neural systems. In parallel, the first Artificial Neural Networks came to life. Since then, the comparative view between brains and computers has been developed in new, sometimes unsuspected directions. With the rise of deep learning and the development of connectomics, an evolutionary look at how both hardware and neural complexity have evolved or designed is required. In this paper, we argue that important similarities have resulted both from convergent evolution (the inevitable outcome of architectural constraints) and inspiration of hardware and software principles guided by toy pictures of neurobiology. Moreover, dissimilarities and gaps originate from the lack of major innovations that have paved the way to biological computing (including brains) that are completely absent within the artificial domain. As it occurs within synthetic biocomputation, we can also ask whether alternative minds can emerge from A.I.\ designs. Here we take an evolutionary view of the problem and discuss the remarkable convergences between living and artificial designs and what are the pre-conditions to achieve artificial intelligence.

Graph neural networks (GNNs) build on the success of deep learning models by extending them for use in graph spaces. Transfer learning has proven extremely successful for traditional deep learning problems: resulting in faster training and improved performance. Despite the increasing interest in GNNs and their use cases, there is little research on their transferability. This research demonstrates that transfer learning is effective with GNNs, and describes how source tasks and the choice of GNN impact the ability to learn generalisable knowledge. We perform experiments using real-world and synthetic data within the contexts of node classification and graph classification. To this end, we also provide a general methodology for transfer learning experimentation and present a novel algorithm for generating synthetic graph classification tasks. We compare the performance of GCN, GraphSAGE and GIN across both the synthetic and real-world datasets. Our results demonstrate empirically that GNNs with inductive operations yield statistically significantly improved transfer. Further we show that similarity in community structure between source and target tasks support statistically significant improvements in transfer over and above the use of only the node attributes.

The commonly-used large-scale knowledge bases have been facing challenges in open domain question answering tasks which are caused by the loose knowledge association and weak structural logic of triplet-based knowledge. To find a way out of this dilemma, this work proposes a novel metaknowledge enhanced approach for open domain question answering. We design an automatic approach to extract metaknowledge and build metaknowledge network from Wiki documents. For the purpose of representing the directional weighted graph with hierarchical and semantic features, we present an original graph encoder GE4MK to model the metaknowledge network. Then a metaknowledge enhanced graph reasoning model MEGr-Net is proposed for question answering, which aggregates both relational and neighboring interactions comparing with R-GCN and GAT. Experiments have proved the improvement of metaknowledge over main-stream triplet-based knowledge. We have found that the graph reasoning models and pre-trained language models also have influences on the metaknowledge enhanced question answering approaches.

Diabetic retinopathy is the most common microvascular complication of diabetes mellitus and one of the leading causes of blindness globally. Due to the progressive nature of the disease, earlier detection and timely treatment can lead to substantial reductions in the incidence of irreversible vision-loss. Artificial intelligence (AI) screening systems have offered clinically acceptable and quicker results in detecting diabetic retinopathy from retinal fundus and optical coherence tomography (OCT) images. Thus, this systematic review and meta-analysis of relevant investigations was performed to document the performance of AI screening systems that were applied to fundus and OCT images of patients from diverse geographic locations including North America, Europe, Africa, Asia, and Australia. A systematic literature search on Medline, Global Health, and PubMed was performed and studies published between October 2015 and January 2020 were included. The search strategy was based on the Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA) reporting guidelines, and AI-based investigations were mandatory for studies inclusion. The abstracts, titles, and full-texts of potentially eligible studies were screened against inclusion and exclusion criteria. Twenty-one studies were included in this systematic review; 18 met inclusion criteria for the meta-analysis. The pooled sensitivity of the evaluated AI screening systems in detecting diabetic retinopathy was 0.93 (95% CI: 0.92-0.94) and the specificity was 0.88 (95% CI: 0.86-0.89). The included studies detailed training and external validation datasets, criteria for diabetic retinopathy case ascertainment, imaging modalities, DR-grading scales, and compared AI results to those of human graders (e.g., ophthalmologists, retinal specialists, trained nurses, and other healthcare providers) as a reference standard. The findings of this study showed that the majority AI screening systems demonstrated clinically acceptable levels of sensitivity and specificity for detecting referable diabetic retinopathy from retinal fundus and OCT photographs. Further improvement depends on the continual development of novel algorithms with large and gradable sets of images for training and validation. If cost-effectiveness ratios can be optimized, AI can become a financially sustainable and clinically effective intervention that can be incorporated into the healthcare systems of low-to-middle income countries (LMICs) and geographically remote locations. Combining screening technologies with treatment interventions such as anti-VEGF therapy, acellular capillary laser treatment, and vitreoretinal surgery can lead to substantial reductions in the incidence of irreversible vision-loss due to proliferative diabetic retinopathy.

The colossal depths of the deep neural network sometimes suffer from ineffective backpropagation of the gradients through all its depths. Whereas, The strong performance of shallower multilayer neural structures prove their ability to increase the gradient signals in the early stages of training which easily gets backpropagated for global loss corrections. Shallow neural structures are always a good starting point for encouraging the sturdy feature characteristics of the input. In this research, a shallow, deep neural structure called PrimeNet is proposed. PrimeNet is aimed to dynamically identify and encourage the quality visual indicators from the input to be used by the subsequent deep network layers and increase the gradient signals in the lower stages of the training pipeline. In addition to this, the layerwise training is performed with the help of locally generated errors which means the gradient is not backpropagated to previous layers, and the hidden layer weights are updated during the forward pass, making this structure a backpropagation free variant. PrimeNet has obtained state-of-the-art results on various image datasets, attaining the dual objective of (1) compact dynamic deep neural structure, which (2) eliminates the problem of backwards-locking. The PrimeNet unit is proposed as an alternative to traditional convolution and dense blocks for faster and memory-efficient training, outperforming previously reported results aimed at adaptive methods for parallel and multilayer deep neural systems.

This study aimed to evaluate cell therapy with human neural precursor cells (hNPCs) in diabetic retinopathy (DR) Wistar rats, induced to diabetes by intraperitoneal injection with streptozotocin. Wharton's Jelly Mesenchymal stem cells (WJ-MSCs) were isolated, expanded, and seeded onto a biopolymer substrate without growth factors to develop neurospheres to obtain the hNPCs, characterized by immunocytochemistry. The animals were divided into three groups; non-diabetic (ND) n = four; diabetic without treatment (DM) n = nine; and diabetic with cell therapy (DM + hNPCs) n = nine. After eight weeks of diabetes induction and verified DR, intravitreal injection of hNPCs (1 x 106 cel/µL) was performed in the DM + hNPCs group. Optical Coherence Tomography (OCT) and Electroretinography (ERG) evaluations were done before and after diabetes induction and after cell therapy. Eye enucleation occurred four weeks after treatment for the histopathological and immunohistochemistry analyses. In the treated group, there was the repair of the retinal structures and their arrangements. hNPCs increased the thickness of neuroretina layers, especially in the ganglion cell and photoreceptor layers. The results indicate that hNPCs reduced DR progression by a neuroprotective effect and promoted retinal repair, making them potential candidates for regeneration of the neuroretinal tissue.

Recently, much attention has been devoted to finding highly efficient and powerful activation functions for CNN layers. Because activation functions inject different nonlinearities between layers that affect performance, varying them is one method for building robust ensembles of CNNs. The objective of this study is to examine the performance of CNN ensembles made with different activation functions, including six new ones presented here: 2D Mexican ReLU, TanELU, MeLU+GaLU, Symmetric MeLU, Symmetric GaLU, and Flexible MeLU. The highest performing ensemble was built with CNNs having different activation layers that randomly replaced the standard ReLU. A comprehensive evaluation of the proposed approach was conducted across fifteen biomedical data sets representing various classification tasks. The proposed method was tested on two basic CNN architectures: Vgg16 and ResNet50. Results demonstrate the superiority in performance of this approach. The MATLAB source code for this study will be available at https://github.com/LorisNanni.

Choline and choline metabolites are essential for all cellular functions. They have also been reported to be crucial for neural development. In this work, we studied the functional characteristics of the choline uptake system in human neural stem cells (hNSCs). Additionally, we investigated the effect of extracellular choline uptake inhibition on the cellular activities in hNSCs. We found that the mRNAs and proteins of choline transporter-like protein 1 (CTL1) and CTL2 were expressed at high levels. Immunostaining showed that CTL1 and CTL2 were localized in the cell membrane and partly in the mitochondria, respectively. The uptake of extracellular choline was saturable and performed by a single uptake mechanism, which was Na+-independent and pH-dependent. We conclude that CTL1 is responsible for extracellular choline uptake, and CTL2 may uptake choline in the mitochondria and be involved in DNA methylation via choline oxidation. Extracellular choline uptake inhibition caused intracellular choline deficiency in hNSCs, which suppressed cell proliferation, cell viability, and neurite outgrowth. Our findings contribute to the understanding of the role of choline in neural development as well as the pathogenesis of various neurological diseases caused by choline deficiency or choline uptake impairment.

With the widespread of embedded sensing capabilities of mobile devices, there has been unprecedented development of context-aware solutions. This allows the proliferation of various intelligent applications such as those for remote health and lifestyle monitoring, intelligent personalized services, etc. However, activity context recognition based on multivariate time series signals obtained from mobile devices in unconstrained conditions is naturally prone to imbalance class problems. This means that recognition models tend to predict classes with the majority number of samples whilst ignoring classes with the least number of samples, resulting in poor generalization. To address this problem, we propose to augment the time series signals from inertia sensors with signals from ambient sensing to train deep convolutional neural networks (DCNN) models. DCNN provides the characteristics that capture local dependency and scale invariance of these combined sensor signals. Consequently, we developed a DCNN model using only inertial sensor signals and then developed another model that combined signals from both inertia and ambient sensors aiming to investigate the class imbalance problem by improving the performance of the recognition model. Evaluation and analysis of the proposed system using data with imbalanced classes show that the system achieved better recognition accuracy when data from inertial sensors are combined with those from ambient sensors such as environment noise level and illumination, with an overall improvement of 5.3% accuracy.

This paper analyzes the robust dissipativity of uncertain stochastic generalized neural networks (USGNNs) with Markovian jumping parameters and time-varying delays. In practical applications most of the systems refer to uncertainties, hence, the norm-bounded parameter uncertainties and stochastic disturbance are considered. Then, by constructing an appropriate Lyapunov-Krasovskii functional (LKF) and by employing integral inequalities LMI-based sufficient conditions of the considered systems are established. Numerical simulations are given to show the merit of the presented results.

This paper investigates the use of deep learning techniques to perform energy demand forecasting. Specifically, the authors have adapted a deep neural network originally thought for image classification and composed of a convolutional neural network (CNN) followed by a multilayered fully connected artificial neural network (ANN). The convolutional part of the network was fed with a grid of temperature forecasting data distributed in the area of interest in order to extract a featured temperature. The subsequent ANN is then fed with this calculated temperature along with other data related to the timing of the forecast. The proposed structure was first trained and then used in a real setting aimed to provide the French energy demand forecast using ARPEGE forecasting weather data. The results show that the performance of this approach is in the line of the performance provided by the reference RTE subscription-based service, which opens the possibility to obtain high accuracy forecasting using widely accessible deep learning techniques through open-source machine learning platforms.

Computational simulation using mathematical models is a useful method for understanding the complex behavior of a living system. The majority of studies using mathematical models to reveal biological mechanisms uses one of the two main approaches: the bottom-up or the top-down approach. When we aim to analyze a large-scale network, such as a comprehensive knowledge-integrated model of a target phenomenon, for example a whole-cell model, the variation of analyses is limited to particular kind of analysis because of the size and complexity of the model. To analyze a large-scale regulatory network of neural differentiation, we developed a hybrid method that combines both approaches. To construct a mathematical model, we extracted network motifs, subgraph structures that recur more often in a metabolic network or gene regulatory network than in a random network, from a large-scale regulatory network, detected regulatory motifs among them, and combined these motifs. We confirmed that the model reproduced the known dynamics of HES1 and ASCL1 before and after differentiation, including oscillation and equilibrium of their concentrations. The model also reproduced the effects of overexpression and knockdown of the Id2 gene. Our model suggests that the characteristic change in HES1 and ASCL1 expression in the large-scale regulatory network is controlled by a combination of four feedback loops, including a large loop which has not been focused on. The model extracted by our hybrid method has the potential to reveal the critical mechanisms of neural differentiation. The hybrid method is applicable to other biological events.

This paper presents a novel approach for indoor acoustic source localization using microphone arrays and based on a Convolutional Neural Network (CNN). The proposed solution is, to the best of our knowledge, the first published work in which the CNN is designed to directly estimate the three dimensional position of an acoustic source, using the raw audio signal as the input information avoiding the use of hand crafted audio features. Given the limited amount of available localization data, we propose in this paper a training strategy based on two steps. We first train our network using semi-synthetic data, generated from close talk speech recordings, and where we simulate the time delays and distortion suffered in the signal that propagates from the source to the array of microphones. We then fine tune this network using a small amount of real data. Our experimental results show that this strategy is able to produce networks that significantly improve existing localization methods based on SRP-PHAT strategies. In addition, our experiments show that our CNN method exhibits better resistance against varying gender of the speaker and different window sizes compared with the other methods.

Intelligent fault diagnosis techniques have replaced the time-consuming and unreliable human analysis, increasing the efficiency of fault diagnosis. Deep learning model can improve the accuracy of intelligent fault diagnosis with the help of its multilayer nonlinear mapping ability. This paper has proposed a novel method named Deep Convolutional Neural Networks with Wide First-layer Kernels (WDCNN). The proposed method uses raw vibration signals as input (data augmentation is used to generate more inputs), and uses the wide kernels in first convolutional layer for extracting feature and suppressing high frequency noise. Small convolutional kernels in the preceding layers are used for multilayer nonlinear mapping. AdaBN is implemented to improve the domain adaptation ability of the model. The proposed model addresses the problem that currently, the accuracy of CNN applied to fault diagnosis is not very high. WDCNN can not only achieve 100% classification accuracy on normal signals, but also outperform state of the art DNN model which is based on frequency features under different working load and noisy environment.

Ultra-wideband wavelength division multiplexed networks enable operators to use more effectively the bandwidth offered by a single fiber pair and thus make significant savings, both in operational and capital expenditures. The main objective of this study is to minimize optical node resources, such as transponders, multiplexers and wavelength selective switches, needed to provide and maintain high quality of network services, in ultra-wideband wavelength division multiplexed networks, at low cost. A model based on integer programming is proposed, which includes a detailed description of optical network nodal resources. The developed optimization tools are used to study the ultra-wideband wavelength division multiplexed network performance when compared with the traditional C-band wavelength division multiplexed networks. The analysis is carried out for realistic networks of different dimensions and traffic demand sets.

Intelligent algorithms are recently used in the optimization process in chemical engineering and application of multiphase flows such as bubbling flow. This overview of modeling can be a great replacement with complex numerical methods or very time-consuming and disruptive measurement experimental process. In this study, we develop the adaptive network-based fuzzy inference system (ANFIS) method for mapping inputs and outputs together and understand the behavior of the fluid flow from other output parameters of the bubble column reactor. Neural cells can fully learn the process in their memory and after the training stage, the fuzzy structure predicts the multiphase flow data. Four inputs such as x coordinate, y coordinate, z coordinate, and air superficial velocity and one output such as pressure gradient are considered in the learning process of the ANFIS method. During the learning process, the different number of the membership function, type of membership functions and the number of inputs are examined to achieve the intelligent algorithm with high accuracy. The results show that as the number of inputs increases the accuracy of the ANFIS method rises up to almost for all cases, while the increment in the number of rules has a effect on the intelligence of artificial algorithm. This finding shows that the density of neural objects or higher input parameters enables the moded for better understanding. We also proposed a new evaluation of data in the bubble column reactor by mapping inputs and outputs and shuffle all parameters together to understand the behaviour of the multiphase flow as a function of either inputs or outputs. This new process of mapping inputs and outputs data provides a framework to fully understand the flow in the fluid domain in a short time of fuzzy structure calculation.

This article describes the use of the PI ProcessBook software tool for visualization and indirect monitoring of occupancy of SHC rooms from the measured operational and technical quantities for monitoring of daily living activities for support of independent life of elderly persons. The proposed method for data processing (predicting the CO₂ course using neural networks from the measured temperature indoor T_i (°C), temperature outdoor T_o (°C) and the relative humidity indoor rHi (%)) was implemented, verified and compared in MATLAB SW tool and IBM SPSS SW tool with IoT platform connectivity. Within the proposed method, the Stationary Wavelet Transform de noising algorithm was used to remove the noise of the resulting predicted course. In order to verify the method, two long-term experiments were performed, (specifically from February 8 to February 15, 2015, from June 8 to June 15, 2015) and two short-term experiments (from February 8, 2015 and from June 8, 2015). For the best results of the trained ANN BRM within the prediction of CO₂, the correlation coefficient R for the proposed method was up to 90%. The verification of the proposed method confirmed the possibility to use the presence of persons of the monitored SHC premises for rooms ADL monitoring.

In recent years, with the development of the Internet of Things and distributed computing, the "server-edge device" architecture has been widely deployed. This study focuses on leveraging autoencoder technology to address the binary classification problem in network intrusion detection, aiming to develop a lightweight model suitable for edge devices. Traditional intrusion detection models face two main challenges when directly ported to edge devices: inadequate computational resources to support large-scale models and the need to improve the accuracy of simpler models. To tackle these issues, this research utilizes Extreme Learning Machine for its efficient training speed and compact model size to implement autoencoders. Two improvements over the latest related work are proposed: First, to improve data purity and ultimately enhance detection performance, this study partitions the data into multiple regions based on the prediction results of these autoencoders. Second, leveraging autoencoder characteristics to investigate further the data within each region. We used the public dataset NSL-KDD to test the behavior of the proposed mechanism. The experimental results show that when dealing with multi-class attacks, the model's performance was significantly improved, the accuracy and the F1-score are improved by 3.5% and 2.9%, respectively maintaining its lightweight nature.

Research in complex network analysis, including tasks such as information dissemination and link prediction, has traditionally advanced by examining groups of nodes with similar characteristics. In multilayer complex networks, these analyses are performed layer-wise, with each layer representing a distinct feature. However, this approach often neglects interlayer interactions, leading to limited predictive power, underestimation of network resilience, and incomplete identification of influential nodes. This article introduces a novel block modeling technique that integrates dominant features from multiple layers, addressing these shortcomings. Our approach introduces a new centrality metric that combines layer weight and PageRank centrality to identify influential nodes within multilayer networks. Nodes are aggregated into blocks centered around these influencers, accounting for both intra- and interlayer connections. Empirical evaluation of various datasets demonstrates that our method effectively identifies influential nodes, thereby enhancing information dissemination and link prediction across diverse multilayer network structures. This technique offers significant potential for improving decision-making processes in various fields, including social network analysis, transportation systems, and biological networks.

The 6TiSCH protocol (IEEE 802.15.4e) is crucial for the Industrial Internet of Things (IIoT), utilizing a time-slotted channel hopping (TSCH) mode based on node distribution. In our experiment, we explored node position clustering and adjusted the capacity of existing cells in congested areas to understand traffic patterns and optimize cell selection for TSCH resource allocation, particularly in slot frames. Efficient cell allocation prevents packet loss, manages congestion, and enhances data transmission reliability. Node clustering increases cell usage efficiency and reduces communication latency between nodes, with each cell allocation tailored to its traffic needs through the sink node from the clustering result. We evaluated the clustering method using the K-means algorithm through experiments using the 6TiSCH simulator. Additionally, we considered using the routing protocol for low power and lossy networks (RPL) as a comparison, such as OF0 and MRHOF, as the objective function to assess clustering results and their impact on throughput and packet delivery. Our method significantly improved average performance metrics: under the OF0 routing protocol, we achieved a 30.01% latency reduction, 15.95% faster joining time, 8% higher packet delivery ratio, and 13.82% throughput increase. Similarly, with the MRHOF routing protocol, we observed a 12.34% improvement in packet delivery ratio, 21.06% latency reduction, 12.68% faster joining time, and 25.97% higher throughput speed.

In recent years, transformer-based models have gained prominence in multivariate long-term time series forecasting (LTSF), demonstrating significant advancements despite facing challenges such as high computational demands, difficulty in capturing temporal dynamics, and managing long-term dependencies. The emergence of LTSF-Linear, with its straightforward linear architecture, has notably outperformed transformer-based counterparts, prompting a reevaluation of the transformer's utility in time series forecasting. In response, this paper presents an adaptation of a recent architecture termed extended LSTM (xLSTM) for LTSF. xLSTM incorporates exponential gating and a revised memory structure with higher capacity that has good potential for LTSF. Our adopted architecture for LTSF termed as xLSTMTime surpasses current approaches. We compare xLSTMTime's performance against various state-of-the-art models across multiple real-world datasets, demonstrating superior forecasting capabilities. Our findings suggest that refined recurrent architectures can offer competitive alternatives to transformer-based models in LTSF tasks, potentially redefining the landscape of time series forecasting.

Clematis Florida (CF) is a folk medicinal herb in the southeast of China, which is traditionally used for treating osteoarticular diseases. However, the mechanism of action remains unclear. The present study used network pharmacology and experimental validation to explore the mechanism of CF in the treatment of rheumatoid arthritis (RA). Liquid chromatography-mass spectrometry (LC-MS/MS) identified 50 main compounds of CF, then the targets of them were obtained from TCMSP, ETCM, ITCM and Swiss TargetPrediction databases. RA disease related targets were obtained from DisGenet, OMIM and GeneCards databases. 99 overlapped targets were obtained using Venn diagram. The protein-protein interaction network (PPI)、the compound-target network (CT) and the compound-potential target genes-signaling pathways network (CPS) were built and analyzed. The results showed that the core compounds were screened as oleanolic acid, oleic acid, ferulic acid, caffeic acid, and syringic acid. And the core therapeutic targets were identified as PTGS2 (COX-2), MAPK1, NF-κB1, TNF, RELA by network pharmacology analysis, which belong to the MAPK signaling pathway and NF-κB signaling pathway. The animal experiments indicated that topical application of CF showed significant anti-inflammatory activity in mice model of xylene-induced ear edema and strong analgesic effect on acetic acid-induced withing. Furthermore, in the rat model of adjuvant arthritis (AA), topical administration of CF could alleviate toe swelling and ameliorate joint damage. The elevation of serum content of IL-6, COX-2, TNF-α, IL-1β, and RF caused by adjuvant arthritis were reduced by CF treatment. Western blotting tests showed that CF may exert regulation on the ERK and NF-κB pathway. The results provided a new perspective for the topical application of CF on RA.

Bacillus subtilis is a model organism used to study molecular processes in Gram-positive bacteria. Sigma factor B, which associates with RNA polymerase, is one of the transcriptional regulators involved in the cell’s response to environmental stress. Experiments have proven that the amounts of free σB (SigB) are controlled by a system of anti- (RsbW) and anti-anti-sigma (RsbV) factors expressed from the same operon as SigB. Moreover, the phosphorylation state of RsbV is controlled by phosphatases RsbP and RsbU, which directly dephosphorylates RsbV. A set of chemical equations describing the network controlling the levels of free SigB was converted to a set of differential equations quantifying the dynamics of the network. The solution of these equations allowed the simulation of the kinetic behavior of the network and its components under real conditions. In this study, the time series of protein expression measured by mass spectrometry were utilized to investigate the role of the phosphatases RsbU/RsbP in transmitting the environmental signal. Additionally, the influence of kinetic constants and the amounts of other network components on the functioning of the network was investigated. A comparison with the same simulation performed using transcriptomic dataset showed that while the time series between the proteomic and transcriptomic datasets) are not correlated, the results are the same. This indicates that when modeling is done within one dataset, it does not matter whether the data come from the mRNA or protein level. In summary, the computational results based on experimental data provide quantitative insight into the functioning of the SigB-dependent circuit and offer a template for the quantitative study of similar systems.

Pulmonary sarcoidosis is a multisystem granulomatous interstitial lung disease (ILD) with a variable presentation and prognosis. Early accurate detection of pulmonary sarcoidosis may prevent progression to pulmonary fibrosis, a serious and potentially life-threatening form of the disease. However, the lack of a gold-standard diagnostic test and specific radiographic findings pose challenges in diagnosing pulmonary sarcoidosis. Chest computed tomography (CT) imaging is commonly used but requires expert, chest-trained radiologists to differentiate pulmonary sarcoidosis from lung malignancies, infections, and other ILDs. In this work, we developed a multichannel, CT and radiomics-guided ensemble network (RadCT-CNNViT) with visual explainability for pulmonary sarcoidosis vs. lung cancer (LCa) classification using chest CT images. We leverage CT and hand-crafted radiomics features as input channels, and a 3D convolutional neural network (CNN) and vision transformer (ViT) ensemble network for feature extraction and fusion before a classification head. The 3D CNN sub-network captures localized spatial information of lesions, while the ViT sub-network captures long-range, global dependencies between features. Through multichannel input and feature fusion, our model achieved the highest performance with accuracy, sensitivity, specificity, and combined AUC of 0.93±0.04, 0.94±0.04, 0.93±0.08 and 0.97 respectively in a 5-fold cross-validation study with pulmonary sarcoidosis (n=126) and LCa (n=93) cases. The model offers promising potential for improving the diagnosis of pulmonary sarcoidosis. A detailed ablation study showing the impact of CNN+ViT compared to CNN or ViT alone, and CT+radiomics input, compared to CT or radiomics alone, is also presented in this work.

Optical backbone networks constitute the fundamental infrastructure employed today by network operators to deliver services to users. As network capacity is a key factor influencing optical network performance, it is important to understand how topological and physical properties impact its behavior and to have the capability to estimate its value. In this context, we propose here a method to evaluate the network capacity that relies on the optical reach to account for physical layer aspects, in conjunction with constrained routing techniques for traffic routing. As this type of routing can lead to traffic blocking, particularly due to the limitation on the number of wavelengths per fiber, we also propose a fiber assignment algorithm designed to deal with this problem. We apply this method to a set of randomly generated networks using a modified Waxman model, and for a network with 60 nodes, in a scenario without blocking, we obtain capacities of about 2.5 Pbit/s for a symbol rate of 64 Gbaud and about 5 Pbit/s for a symbol rate of 128 Gbaud. Remarkably, this duplication in the total network capacity is achieved by an increase in the total fiber length of only about 51%.

Image stitching is a crucial aspect of image processing. However, factors like perspective and environment often lead to irregular shapes in stitched images. Cropping or completion methods typically result in substantial loss of information. This paper proposes a method for rectifying irregularly images into rectangles using deformable meshes and residual networks. The method utilizes a convolutional neural network to quantify rigid structures of images. Choosing the most suitable mesh structure based on the extraction results, offering options such as triangular, rectangular, and hexagonal. Subsequently, the irregularly image, predefined mesh structure, and predicted mesh structure are input into a wide residual neural network for regression. The loss function comprises local and global, aimed at minimizing the loss of image information within the mesh and global target. This method not only significantly reduces information loss during rectification but also adapting to different images with various rigid structures. Validation on the DIR-D dataset shows this method outperforms state-of-the-art methods in image rectification.

Skin cancer is a prevalent type of malignancy on a global scale, and the early and accurate diag-nosis of this condition is of utmost importance for the survival of patients. The clinical assessment of cutaneous lesions is a crucial aspect of medical practice, although it encounters several obsta-cles, such as prolonged waiting time and misinterpretation. The intricate nature of skin lesions, coupled with variations in appearance and texture, presents substantial barriers to accurate clas-sification. As such, skilled clinicians often struggle to differentiate benign moles from early ma-lignant tumors in skin images. Although deep learning-based approaches such as convolution neural networks have made significant improvements, their stability and generalization continue to confront difficulties, and their performance in accurately delineating lesion borders, capturing refined spatial connections among features, and using contextual information for classification is suboptimal. To address these limitations, we propose a novel approach for skin lesion classification which combines snake models of Active Contour (AC) Segmentation, ResNet50 for feature ex-traction and a Capsule Network with a fusion of lightweight attention mechanisms, to attain the different feature channels and spatial regions within feature maps, enhance the feature discrimi-nation, and improve accuracy. We employed the Stochastic Gradient Descent (SGD) optimization algorithm to optimize the model's parameters. The proposed model is implemented on publicly available datasets, namely HAM10000 and ISIC 2020. The experimental results showed that the proposed model achieved an accuracy of 98% and AUC-ROC of 97.3%, showcasing substantial potential in terms of effective model generalization compared to existing state-of-the-art (SOTA) approaches. These results highlight the potential for our approach to reshape automated derma-tological diagnosis and provide a helpful tool for medical practitioners.

Image stitching is a crucial aspect of image processing. However, factors like perspective and environment often lead to irregular shapes in stitched images. Cropping or completion methods typically result in substantial loss of information. This paper proposes a method for rectifying irregularly images into rectangles using deformable meshes and residual networks. The method utilizes a convolutional neural network to quantify rigid structures of images. Choosing the most suitable mesh structure based on the extraction results, offering options such as triangular, rectangular, and hexagonal. Subsequently, the irregularly image, predefined mesh structure, and predicted mesh structure are input into a wide residual neural network for regression. The loss function comprises local and global, aimed at minimizing the loss of image information within the mesh and global target. This method not only significantly reduces information loss during rectification but also adapting to different images with various rigid structures. Validation on the DIR-D dataset shows this method outperforms state-of-the-art methods in image rectification.

Carotid intima-media thickness (CIMT) is a surrogate indicator for atherosclerosis and has been shown to predict cardiovascular risk in multiple large studies. Identifying and characterizing molecular markers for carotid atheroma plaque formation can be critical for early intervention and prevention of atherosclerosis. This study performed transcription factor (TF) network analysis of transcriptomic data focusing on two TF genes, ZNF385D, HAND2, whose polymorphisms reportedly associate with carotid atherosclerosis. Gene expression data were measured from pieces of carotid endarterectomy of hypertensive patients each paired with one sample of distant macroscopically intact tissue. TF networks were reconstructed for ZNF385D and HAND2 and their association with carotid atheroma progression examined using gene-set enrichment analysis with high statistical significance (p<6.95e-7) suggesting involvement of expression quantitative loci (eQTL). Examination of the regulation and correlation patterns suggests high clinical and interventional impacts of the two TF genes on impairing carotid atheroma plaque formation and preventing carotid atherosclerosis.

The COVID-19 pandemic brought about a significant change in mobility habits within cities, with a significant decrease in the use of collective urban transport that has only been partially and unevenly reversed. To recover the previous rates of use, many cities are analyzing which characteristics of the urban transport network are hindering this recovery process in order to design actions to promote sustainable mobility. This article shows a study carried out in the city of Almería (Spain), where the operation variables of the municipal bus network have been analyzed (frequency, average vehicle occupancy, length of the lines, urban or suburban character, circularity, nodality or intermodality) to detect what aspects are more determinant on the number of users recovered. The results show that the lines that have recovered the most users in average are suburban lines, as well as the nodal lines that serve key centroids such as the university. Thus, the dependence of users on public transport would be the most important determinant in recovery, more than other variables representative of the service´s intrinsic quality. This result shows that, without compromising the necessary quality of the service, the restrictions on less sustainable transportation alternatives will be those that, to a greater extent, allow for the prompt recovery of the space lost by urban public transportation.

Understanding the impact of drought stress on Arabica coffee physiology and metabolism is essential in the pursuit of developing drought-resistant varieties. In this study, we explored the physiological and metabolite changes in coffee genotypes exhibiting varying degrees of tolerance to drought—namely, the relatively tolerant Ca74110 and Ca74112, and the sensitive Ca754 and CaJ-19—under well-watered conditions and during terminal drought stress periods over two-time intervals (0 and 60 days following the onset of stress). The Metabolites profiling conducted uncovered significant associations between growth and the physiological characteristics of coffee genotypes with distinct drought tolerance behaviors. Initially, no marked differences were observed among genotypes or treatments. However, at the 60-day post-drought onset, notable increases in shoot growth, biomass, CO2 assimilation, pigments, and various physiological parameters were evident, particularly in the relatively tolerant genotypes. Metabolite profiling revealed elevations in glucose, maltose, amino acids, organic acids, and decreases in other metabolites, more pronounced in drought-tolerant genotypes. These alterations were more pronounced in the drought-tolerant genotypes, indicating a correlation with enhanced compatible solutes and energy-associated metabolites crucial for drought tolerance mechanisms. This research introduces GC-MS based metabolome profiling to Ethiopian coffee, shedding light on the intricate responses to drought stress and paving the way for the potential development of drought-resistant coffee seedlings in intensified agro-ecological zones.

Defect detection plays a pivotal role in quality control for fabrics. In order to enhance the accuracy and efficiency of fabric defect detection, we have proposed the PRC-Light YOLO model for fabric defect detection and have established a detection system. Firstly, we add new convolution operators in Backbone for the YOLOv7 and integrate them with Extended-Efficient Layer Aggregation Network. This combination constructs a new feature extraction module that not only reduces the computational effort of the network model, but also extracts spatial features effectively. Secondly, we employ multi-branch dilated convolutions feature pyramid, and introduce lightweight upsampling operators to improve performance of the feature fusion network. This module achieves an expanded receptive field by generating real-time adaptive convolution kernels, allowing for the collection of crucial information from regions with a richer contextual context. To further minimize the computation during network model training, we adopt the HardSwish activation function. Finally, we apply the Wise-IOU v3 bounding box loss function as a dynamic non-monotonic focusing mechanism, which decreases adverse gradients from low-quality instances. We conduct data augmentation on real fabric dataset to raise the generalization capability of the PRC-Light YOLO model. Compared with the YOLOv7 model, numerous simulation experiments show that our proposed methods reduce the model’s parameters and computation by 18.03% and 20.53%, respectively. Simultaneously, there has been a 7.6% improvement in mAP.

In this study, we present a federated learning approach that combines a multi-branch network and the Oort client selection algorithm to improve the performance of federated learning systems. This method successfully addresses the significant issue of non-iid data, a challenge not adequately tackled by the commonly used MFedAvg method. Additionally, one of the key innovations of this research is the introduction of uniformity, a metric that quantifies the disparity in training time amongst participants in a federated learning setup. This novel concept not only aids in identifying stragglers but also provides valuable insights into assessing the fairness and efficiency of the system. Experimental results underscore the merits of the integrated multi-branch network with the Oort client selection algorithm and highlight the crucial role of uniformity in designing and evaluating federated learning systems.

The consequences of climate change and anthropogenic stressors, such as habitat loss and overexploitation, are threatening the subsistence of species and communities across the planet. Therefore, it is crucial to analyze the impact of environmental perturbations on the diversity, structure and function of ecosystems. In this work, in silico simulations of biodiversity loss were carried out on the marine food web of Caleta Potter (25 de Mayo Island, Antarctica) where global warming has caused critical changes in the abundance and distribution of benthic and pelagic communities during the last 30 years. We performed species removal considering their degree and trophic level and including four different thresholds on the occurrence of secondary extinctions. We examined the impact of extinctions on connectance, modularity and stability of the food web. We found different responses of these properties depending on the extinction criteria used, e.g., large increase in modularity and rapid decrease in stability when most-connected and relatively high-trophic level species were removed. Additionally, we studied the complexity-stability relationship of the food web founding two regimes: 1) high sensitivity to small perturbations suggesting that Potter Cove would be locally unstable, and 2) high persistence to long-range perturbations suggesting global stability of this ecosystem.

While most published research on COVID-19 focused in a few countries and especially during the second wave of the pandemic and the vaccination period, we turn to the first wave (march-May 2020) to examine sentiment and emotions expressed by Twitter users in Greece. We use computational methods combining opinion mining and the application of a modified emotion lexicon with Social Network Analysis to explore the subtleties behind an overarching negative sentiment. Our analysis has shown that popular sentiment isn’t stable nor monolithic, since underlying emotions may be a better predictor of attitudes during a crisis.

Intrauterine adhesions (IUA) has become one of the main causes of female infertility, how to effectively prevent postoperative re-adhesion has been a clinical challenge. In this study, a mussel-inspired dual-network hydrogel was proposed for postoperative anti-adhesion of IUA. First, calcium alginate/polyacrylamide (CA-PAM) hydrogel was prepared by covalent and Ca2+ cross-linking. Benefiting from abundant phenolic hydroxyl groups, polydopamine (PDA) was introduced to further enhance the adhesion ability and biocompatibility. This CA-PAM hydrogel immersed in 10 mg/mL dopamine solution possessed remarkable mechanical strength (elastic modulus > 5 kPa) and super stretchability (with a breaking elongation of 720%). At the same time, it shown excellent adhesion more than 6 kPa. Surprisingly, the coagulation index of the hydrogel was 27.27 ± 4.91, demonstrating attractive coagulation performance in vitro and the potential for rapid hemostasis after surgery.

Variation in metabolite profiles of under high salinity and nitrogen constraint conditions are the key issues of study at the present. To investigate the optimum NaCl and NaNO3 concentration and the corresponding metabolic pathways of astaxanthin accumulation in H. pluvialis, a 26-day batch culture experiment of H. pluvialis treated under the variable concentration gradients of NaCl and NaNO₃ were conducted. The results indicated that 7.5g•L^-1 and nitrogen-deficient were the optimum NaCl and NaNO₃ concentration for the astaxanthin accumulation according to single factor experiments respectively, under which the highest contents of astaxanthin accumulated in H. pluvialis reached up to 7.51mg•L^-1 and 5.60mg•L^-1. A total of 132 metabolites were analysed using LC-MS/MS technique, among which 30 differential metabolites with statistical significance were highlighted. Subsequently, 18 and 10 differential metabolic pathways in the high salinity and nitrogen-deficient treatments with statistic significance were enriched and annotated respectively. Furthermore, the metabolic networks related to the astaxanthin accumulation were constucted based on the crucial pathways and metabolites. Moreover, the major carbon metabolism in H. pluvialis under the high salinity and nitrogen deficient stress were presented, which exhibited the characteristics in the identified metabolites changes under the different stress conditions. The results did not only demonstrate the differential metabolic networks and the distinct changes in the metabolites involved in the major carbon metabolism, related to the astaxanthin accumulation in H. pluvialis under the different stress factors, but provided the regulation targets for astaxanthin production in practice.

Track fasteners play a pivotal role in infrastructure inspection for high-speed rail. Yet, images taken by drones often capture shadows cast by electrical towers flanking the high-speed rail tracks. These shadows can hinder the visibility of the track fasteners, thereby impacting detection efficiency and accuracy considerably. The present paper introduces an end-to-end shadow removal algorithm, rooted in generative adversarial network training. The comprehensive network framework is segmented into three sub-networks: pseudo-mask generation, shadow removal, and result refinement. We have integrated a Fourier convolutional residual module to bolster the feature extraction capability of the generator network. This integration ensures the network retains a global receptive field, even in its more superficial layers. By employing an overall weighted loss function, we enhance the quality of the images produced without shadows. Further, a perceptual loss function has been incorporated to retain the structural information of objects, setting the stage for subsequent defect detection. Our results highlight that Pse-ShadowNet adeptly eradicates fastener shadows while maintaining vital visual features, including object position, structure, texture, edges, and other key visual elements. Consequently, the reconstructed images are detailed and showcase superior image quality.

Network neuroscience delves into comprehending the intricate arrangement and interactions within the neural networks of the brain. By merging insights from both neuroscience and network theory, it investigates the brain's structure and function through the lens of interconnected nodes (symbolizing brain regions) and edges (symbolizing the connections among these regions) forming a dynamic network. Graph metrics play a pivotal role in neuroscience by providing quantifiable insights into the intricate connectivity patterns within the brain's neural networks. Frequently, nodes are extracted from functional or structural atlases, which can lead to diverse shapes and sizes. Nevertheless, our understanding of how these differing node characteristics and definitions impact the computed graph metrics in neuroimaging data remains limited. This study adopts a data-driven methodology to delineate functional nodes, subsequently examining the influence of their sizes on resultant graph metrics. By employing the Neuromark framework, an entirely automated independent component analysis (ICA) is applied to resting state fMRI data. Through this, functional network connectivity (FNC) matrices are computed—capturing Pearson correlations between component-time courses—while employing a proportional threshold to streamline node connections based on these correlations. Subsequently, various global and local graph metrics are computed, offering insights into network characteristics. Global metrics provide an overarching summary of the network structure, while local measures delve into structural intricacies at the individual component level. Node sizes are computed based on voxel counts surpassing a designated threshold. Next, we calculated the Pearson correlation between the obtained node sizes and the graph metrics, which we term 'node-metric coupling' (NMC). Our findings revealed consistent and noteworthy correlations between the values of graph metrics and the dimensions of brain nodes. To delve deeper into the implications of this correlation, we examined the node-metric coupling within a dataset comprising Alzheimer's disease, mild cognitive impairment, and control subjects. The disparities observed in node-metric coupling among these groups underscore the necessity of accounting for this factor during analysis. The two principal outcomes of this study are as follows: Firstly, the substantial interplay between varying node sizes within a given atlas and the resultant graph metrics; and secondly, the potential utility of node-metric coupling as a viable biomarker for brain disorders. These discoveries hold significant ramifications. While comparing studies employing diverse atlases is already a challenge, our work highlights an additional, critical source of variability: accounting for node sizes. Consequently, the association between intra-atlas node size and graph metric should be thoughtfully acknowledged in future neuroimaging investigations.

Recently, the triple-network convergence system (TNCS) has emerged from the deep integration of the power grid, transportation network, and information network. Fault recovery research in the TNCS is important since this system's complexity and interactivity can expand the faults scale and increase faults impact. Currently, fault recovery focuses primarily on single power grids and cyber-physical systems, but there are certain shortcomings, such as ignoring uncertainties including generator start-up failures and the occurrence of new faults during recovery, energy supply-demand imbalances leading to system security issues and communication delay caused by network attacks. In this study, we propose a recovery method based on the improved TD3 algorithm, factoring in shortcomings of the existing research. Specifically, we establish a TNCS model to analyze interaction mechanisms and design a state matrix to represent the uncertainty changes in the TNCS, a negative reward to reflect the impact of unit start-up failures, a special reward to reflect the impact of communication delay and an improved Actor network update mechanism. Experimental results show that our method obtains the optimal recovery decisions, maximizes restoration benefit in power grid failure scenarios and demonstrates a strong resilience against communication delay caused by DoS attacks.

Over the years, network analysis became a promising strategy to analyze complex system, i.e. systems composed by a large number of interacting elements. In particular, multilayer networks have emerged as a powerful framework for modelling and analysing complex systems with multiple types of interactions. Network analysis can be applied to pharmacogenomics to gain insights into the interactions between genes, drugs, and diseases. By integrating network analysis techniques with pharmacogenomic data, the goal consists to uncover complex relationships and identify key genes to use in pathway enrichment analysis to figure out biological pathways involved in drug response and adverse reactions. In this study, we model omics, diseases and drugs data together through the multilayer network representation. Then, we mined the multilayer network with a community detection algorithm by obtaining top communities. After that, we used the identified list of genes from the communities to perform pathway enrichment analysis (PEA) to figure out the biological function affected form the selected genes. The results show that the genes forming the top community have the multiple roles through different pathways.

Most of the literature on the optimization problem of transportation in supply chain networks (SCN) considered fixed costs (FC). However, in the practical applications of this problem it is important to study the effect of FC. This paper examines the impact of fixed cost increase as well as the variable cost on the optimization of a Two-Stage SCN. To do so, two mathematical models for mixed-integer nonlinear programming are developed. The first model optimizes fixed and variable costs in addition to the opening cost, whereas the second model only optimizes variable and opening costs. To evaluate the effect of considering FC on the optimization supply chain problem, four groups of instances are randomly generated, and solved using Lingo. The results of the two models are compared utilizing the average percentage deviation. In addition, sensitivity analysis is performed to determine the impact of changes in opening and variable costs on the considered optimization problem. The computational results and the sensitivity analysis show that the first model with minimized FC outperforms the second model, which does not consider the FC in minimization and FC affect the optimization.

In network analysis, links depict the connections between each pair of network nodes. However, such pairwise connections fail to consider the interactions among more agents, which may be indirectly connected. Such non-pairwise or higher-order connections can be signified by involving simplicial complexes. The higher-order connections become even more noteworthy when it comes to neuronal network synchronization, an emerging phenomenon responsible for the many biological processes in real-world phenomena. However, involving higher-order interactions may considerably increase the computational costs. To confound this issue, map-based models are more suitable since they are faster, simpler, more flexible, and computationally more optimal. Therefore, this paper addresses the impact of pairwise and non-pairwise neuronal interactions on the synchronization state of 10 coupled memristive Hindmarsh-Rose neuron maps. To this aim, electrical, inner linking, and chemical synaptic functions are considered as 2- and 3-body interactions in three homogenous and two non-homogenous cases. The results show that through chemical pairwise and non-pairwise synapses, the neurons achieve synchrony with the weakest coupling strengths.

To reveal the relationship between metallodrugs and cancer malignancy, molecular networks of anti-cancer drugs were analyzed. Molecular networks in several types of cancers were analyzed in Ingenuity Pathway Analysis (IPA). Analysis of carboplatin revealed the causal network in diffuse large B-cell lymphoma. Analysis of 12 analyses of cisplatin treatment identified causal networks including camptothecin and NUPR1. The causal network of camptothecin, which includes PTEN, FAS, and IRF1, was inactivated in diffuse-type GC and activated in intestinal-type GC. Upstream regulator analysis of cisplatin revealed an increase in FAS, BTG2, SESN1 and CDKN1A, and the involvement of the tumor microenvironment pathway. Upstream regulators of cisplatin-treated lung adenocarcinoma included a histone deacetylase inhibitor, trichostatin A (TSA). Causal network of arsenic was inactivated in diffuse-type GC and activated in intestinal-type GC, and included ERK, EGFR, SRC, IKK and TP53. Prediction of RNA-RNA interactions with the causal network of arsenic identified 10 microRNAs including mir-101, mir-103, and mir-22. The results revealed the involvement of EMT in arsenic treatment. Analysis of oxaliplatin, a platinum drug, revealed that the SPINK1 pancreatic cancer pathway is inactivated in ischemic cardiomyopathy. The study showed the importance of the relationship between platinum drugs or arsenic trioxide and the tumor microenvironment in the treatment of resistant cancer in humans.

Fake news detection has become a significant topic based on the fast-spreading and detrimental effects of such news. Many methods based on deep neural networks learn clues from claim content and message propagation structure or temporal information, which have been widely recognized. However, such models (i) ignore the fact that information quality is uneven in propagation, which makes semantic representations unreliable. (ii) Most models do not fully leverage spatial and temporal structure in combination. (iii) Finally, internal decision-making processes and results are non-transparent and unexplained. In this study, we develop a trust-aware evidence reasoning and spatiotemporal feature aggregation model for more interpretable and accurate fake news detection. Specifically, we first design a trust-aware evidence reasoning module to calculate the credibility of posts based on a random walk model to discover high-quality evidence. Next, from the perspective of spatiotemporal structure, we design an evidence-representation module to capture the semantic interactions granularly and enhance the reliable representation of evidence. Finally, a two-layer capsule network is designed to aggregate the implicit bias in evidence while capturing the false portions of source information in a transparent and interpretable manner. Extensive experiments on two benchmark datasets indicate that the proposed model can provide explanations for fake news detection results, as well as can achieve better performance, boosting 3.5% in F1-score on average.

This study analysed through the perspective of networks the association between physical activity (PA), sedentary behaviour (SB), and cardiovascular risk factors in overweight low-income schoolchildren from the perspective of complex systems. Methods: The sample consisted of 41 overweight children between 6 and 10 years old (56% girls). PA and SB were analysed by accelerometer, and the measures of cardiovascular factor risk were: anthropometric and hemodynamic measurements, body fat, lipid profile and glucose, cardiorespiratory fitness (CRF), left ven-tricular mass (LVM), and Sokolov-Lyon. Network analysis with Boot-strap-1000 was performed to analyze the association between PA, SB and the cardiovascular risk factors. Results: Moderate to vigorous PA was positive related with Waist circumference (WC; 0.499), HDL-C (0.307), and CRF (0.276), and negatively associated with BMI (-0.251) and Fat (-0.341). For SB, positive associations were seen with WC (0.326), CRF (0.296), LVM (0.250) and Sokolov (0.215). Adicionalment, the centrality indicators highlighted WC as the most important variable in the network. Conclu-sion: Interventions that aim to mitigate the harmful effects of obesity on cardiovascular risk factors in overweight children should consider WC as an important variable in of system.

Between October 2021 and April 2022, 317 outbreaks caused by highly pathogenic avian influen-za (HPAI) H5N1 viruses were notified in poultry farms in the northeastern Italian Regions. The complete genomes of 214 strains were used to estimate the genetic network based on the virus similarity. An exponential random graph model (ERGM) was used to assess the effect of at-risk contacts, same owners, in-bound/out-bound risk windows overlap, genetic differences, geograph-ic distances, same species and poultry company, on the probability of observing a link within the genetic network, which can be interpreted as the potential propagation of the epidemic via lateral spread or a common source of infection. The variables same poultry company (Est.=0.548, C.I.=[0.179;0.918]) and risk windows overlap (Est.=0.339, C.I.=[0.309;0.368]) were associated with a higher probability of link formation, while the genetic differences (Est.=-0.563, C.I.=[-0.640;-0.486]) and geographic distances (Est.=-0.058, C.I.=[-0.078;-0.038]) indicated a re-duced probability. The integration of epidemiological data with genomic analyses allows moni-toring the epidemic evolution and helps explain the dynamics of lateral spreads suggesting the potential diffusion routes. The 2021-2022 epidemic stresses the need to further strengthen the bi-osecurity measures, and to encourage the reorganisation of the poultry production sector to mini-mize the impact of future epidemics.

As a conceptual model of disease mechanisms, a disease map integrates available knowledge and is applied for data interpretation, predictions and hypothesis generation. It is possible to model disease mechanisms on different levels of granularity and adjust the approach to the goals of a particular project. This rich environment together with requirements for high-quality network reconstruction makes it challenging for new curators and groups to be quickly introduced to the development methods. In this review, we offer a step-by-step guide for developing a disease map within its mainstream pipeline that involves using the CellDesigner tool for creating and editing diagrams and the MINERVA Platform for online visualisation and exploration. We also describe how the Neo4j graph database environment can be used for managing and querying efficiently such a resource. For assessing the interoperability and reproducibility we apply FAIR principles.

Working memory refers to the capability of the nervous system to selectively retain short-term memories in an active state. The long-standing viewpoint is that neurons play an indispensable role and working memory is encoded by synaptic plasticity. Furthermore, some recent studies have shown that calcium signaling assists the memory processes and the working memory might be affected by the astrocyte density. Over the last few decades, growing evidence has also revealed that astrocytes exhibit diverse coverage of synapses which are considered to participate in neuronal activities. However, very little effort has yet been made to attempt to shed light on the potential correlations between these observations. Hence, in this article we will leverage a computational neuron-astrocyte model to study the short-term memory performance subject to various astrocytic coverage and we will demonstrate that the short-term memory is susceptible to this factor. Our model may also provide plausible hypotheses for the various sizes of calcium events as they are reckoned to be correlated with the astrocytic coverage.

This paper introduces a multi-class hand gesture recognition model developed to identify a set of defined hand gesture sequences in two-dimensional RGB video recordings. The work presents an action detection classifier that looks at both appearance and spatiotemporal parameters of consecutive frames. The classifier utilizes a convolutional-based network combined with a long-short-term memory unit. To leverage the need for a large-scale dataset, the model uses an available dataset to then adopt a technique known as transfer learning to fine-tune the model on the hand gestures of relevance. Validation curves performed over a batch size of 64 indicate an accuracy of 93.95% (± 0.37) with a mean Jaccard index of 0.812 (± 0.105) for 22 participants. The presented model illustrates the possibility of training a model with a small set of data (113,410 fully labelled frames). The proposed pipeline embraces a small-sized architecture that could facilitate its adoption.

Seismic monitoring in areas where induced earthquakes could occur is a challenging topic for seismologists due to generally very low signal to noise ratio. Therefore, the seismological com-munity is devoting several efforts to the development of high-quality networks around the areas where fluid injection and storage and geothermal activities take place, also following the national induced seismicity monitoring guidelines. The use of advanced data-mining strategy, such as template matching filters, auto-similarity search and deep-learning approaches is recently further fostering such a monitoring enhancing the seismic catalogues and lowering the magnitude of completeness of these areas. In this framework, we carried out an experiment where a small-aperture seismic array was installed around the gas reservoir of Collalto, in North Italy. The continuous velocimetric data, acquired for 25 days, were analysed through the application of the optimized auto-similarity search technique FAST. The array was conceived as a cost-effective network, aimed at integrating, right above the gas storage site, the permanent high-resolution Collalto Seismic Network. The analysis allowed to detect micro-events down to magnitude Ml=-0.4 within a distance of ~15km from the array. Our results confirmed that the system based on the array installation and the FAST data-analysis might contribute to lower the magnitude of completeness around the site of about 0.7.

Since the 1970s, researchers in international relations have asserted that the enhancement of interdependence between nations can reduce conflicts among them (Keohane and Nye 1973). Thus, interdependency between nations is regarded as desirable for the stability of the countries' networks. On the other hand, there has been no confirmation of empirical data on the benevolent effects of interdependency on the nations' networks. This article aims to analyze the concept of interdependence into reciprocity and dependence, leading to quantifying both of them. To assess the usefulness of this approach, the empirical analysis of trade relations among five countries, namely, THE U.S.., China, Germany, Japan, and Korea from 1992 to 2020 was empirically analyzed with the aid of reciprocity index (R) and dependency index (D).

HIV-associated neurocognitive disorder (HAND) is an array of neurocognitive changes associated with HIV infection, and the roles of microRNAs in HAND are not completely revealed yet. Based on published data and publicly available databases, we constructed an integrated miRNA-mRNA network involved in HAND. Bioinformatics analyses, including gene ontology, network analysis, and KEGG pathway analysis, were applied for further study of the network and the genes of the network. The axon guidance KEGG pathway, three genes NTNG1, EFNB2, CXCL12, and 17 miRNAs which regulates them, are spotlighted in our study. This study provides new perspectives to the knowledge of miRNAs’ roles in the process of HAND, and our findings provided potential therapeutic targets and clues of HAND.

As V2X technology develops, acute problems related to reliable and secure information exchange between network objects in real time appear. The article aims to solve the scientific problem of building a network architecture for reliable delivery of correct and uncompromised data within the V2X concept to improve the safety of road users, using blockchain technology and mobile edge computing (MEC). The authors present a formalized mathematical model of the system, taking into account the interconnection of objects and V2X information channels, and an energy-efficient algorithm of traffic offloading to the MEC server. The paper presents the results of application of blockchain technologies and mobile edge computing in the developed system, their description, evaluation of advantages and disadvantages of the implementation.