Function Network Approach Research Articles

Network-level traffic flow prediction: Functional time series vs. functional neural network approach

Network-level traffic flow prediction: Functional time series vs. functional neural network approach

The TiHoCL panel for canine lymphoma: a feasibility study integrating functional genomics and network biology approaches for comparative oncology targeted NGS panel design.

Targeted next-generation sequencing (NGS) enables the identification of genomic variants in cancer patients with high sensitivity at relatively low costs, and has thus opened the era to personalized human oncology. Veterinary medicine tends to adopt new technologies at a slower pace compared to human medicine due to lower funding, nonetheless it embraces technological advancements over time. Hence, it is reasonable to assume that targeted NGS will be incorporated into routine veterinary practice in the foreseeable future. Many animal diseases have well-researched human counterparts and hence, insights gained from the latter might, in principle, be harnessed to elucidate the former. Here, we present the TiHoCL targeted NGS panel as a proof of concept, exemplifying how functional genomics and network approaches can be effectively used to leverage the wealth of information available for human diseases in the development of targeted sequencing panels for veterinary medicine. Specifically, the TiHoCL targeted NGS panel is a molecular tool for characterizing and stratifying canine lymphoma (CL) patients designed based on human non-Hodgkin lymphoma (NHL) research outputs. While various single nucleotide polymorphisms (SNPs) have been associated with high risk of developing NHL, poor prognosis and resistance to treatment in NHL patients, little is known about the genetics of CL. Thus, the ~100 SNPs featured in the TiHoCL targeted NGS panel were selected using functional genomics and network approaches following a literature and database search that shielded ~500 SNPs associated with, in nearly all cases, human hematologic malignancies. The TiHoCL targeted NGS panel underwent technical validation and preliminary functional assessment by sequencing DNA samples isolated from blood of 29 lymphoma dogs using an Ion Torrent™ PGM System achieving good sequencing run metrics. Our design framework holds new possibilities for the design of similar molecular tools applied to other diseases for which limited knowledge is available and will improve drug target discovery and patient care.

Forest Certification in the Context of the Functional Complex Network Approach for Forest Management

Forest Certification in the Context of the Functional Complex Network Approach for Forest Management

Functional tensor network solving many-body Schrödinger equation

Schr\"odinger equation belongs to the most fundamental differential equations in quantum physics. However, the exact solutions are extremely rare, and many analytical methods are applicable only to the cases with small perturbations or weak correlations. Solving the many-body Schr\"odinger equation in the continuous spaces with the presence of strong correlations is an extremely important and challenging issue. In this work, we propose the functional tensor network (FTN) approach to solve the many-body Schr\"odinger equation. Provided the orthonormal functional bases, we represent the coefficients of the many-body wave-function as tensor network. The observables, such as energy, can be calculated simply by tensor contractions. Simulating the ground state becomes solving a minimization problem defined by the tensor network. An efficient gradient-decent algorithm based on the automatically differentiable tensors is proposed. We here take matrix product state (MPS) as an example, whose complexity scales only linearly with the system size. We apply our approach to solve the ground state of coupled harmonic oscillators, and achieve high accuracy by comparing with the exact solutions. Reliable results are also given with the presence of three-body interactions, where the system cannot be decoupled to isolated oscillators. Our approach is simple and with well-controlled error, superior to the highly-nonlinear neural-network solvers. Our work extends the applications of tensor network from quantum lattice models to the systems in the continuous space. FTN can be used as a general solver of the differential equations with many variables. The MPS exemplified here can be generalized to, e.g., the fermionic tensor networks, to solve the electronic Schr\"odinger equation.

Using a Novel Functional Brain Network Approach to Locate Important Nodes for Working Memory Tasks.

Working Memory (WM) is a short-term memory for processing and storing information. When investigating WM mechanisms using Electroencephalogram (EEG), its rhythmic synchronization properties inevitably become one of the focal features. To further leverage these features for better improve WM task performance, this paper uses a novel algorithm: Weight K-order propagation number (WKPN) to locate important brain nodes and their coupling characteristic in different frequency bands while subjects are proceeding French word retaining tasks, which is an intriguing but original experiment paradigm. Based on this approach, we investigated the node importance of PLV brain networks under different memory loads and found that the connectivity between frontal and parieto-occipital lobes in theta and beta frequency bands enhanced with increasing memory load. We used the node importance of the brain network as a feature vector of the SVM to classify different memory load states, and the highest classification accuracy of 95% is obtained in the beta band. Compared to the Weight degree centrality (WDC) and Weight Page Rank (WPR) algorithm, the SVM with the node importance of the brain network as the feature vector calculated by the WKPN algorithm has higher classification accuracy and shorter running time. It is concluded that the algorithm can effectively spot active central hubs so that researchers can later put more energy to study these areas where active hubs lie in such as placing Transcranial alternating current stimulation (tACS).

NURBS functional network approach for automatic image segmentation of macroscopic medical images in melanoma detection

Image processing techniques are becoming standard technology in many medical specialities, such as dermatology, where they are a key tool for the early detection and diagnosis of melanoma and other skin cancers and tumors. A previous paper by the authors presented at SOCO 2020 conference introduced a new method for image segmentation of skin images through functional networks. The method performs well but it relies on a semi-automatic approach involving a combination of manual and automatic operations. This paper aims at making image segmentation of macroscopic skin images a fully automatic process. To this purpose, the present work extends our previous paper with five new relevant contributions: (1) a filtering strategy for removal of noise, hair and other artifacts; (2) two morphological operators for image enhancement; (3) a clustering-based binary classifier to separate the skin tumor from the image background; (4) a smoothing and discretization process to obtain the border points; and (5) a curve reconstruction method from the border points with NURBS using a new type of functional network particularly tailored for this task. This new method is applied to two different benchmarks, comprised respectively of four and two macroscopic medical images of skin tumors. The visual and numerical results show that the method performs very well, yielding segmented images which are suitable for clinical practice. This method is a significant step towards the future development of a fully automatic approach for the whole medical image analysis pipeline of skin images, including diagnosis and classification.

Diffuseness effect and radial basis function network for optimizing α decay calculations * *Supported by the National Natural Science Foundation of China (11947229, 11675223, 11675066), the China Postdoctoral Science Foundation (2019M663853), the Fundamental Research Funds for the Central Universities (lzujbky-2017-ot04) and Feitian Scholar Project of Gansu province

A radial basis function network (RBFN) approach is adopted for the first time to optimize the calculation of decay half-life in the generalized liquid drop model (GLDM), while concurrently incorporating the surface diffuseness effect. The calculations presented herein agree closely with the experimental half-lives for 68 superheavy nuclei (SHN), achieving a remarkable reduction of 40% in the root-mean-square (rms) deviations of half-lives. Furthermore, using the RBFN method, the half-lives for four SHN isotopes, 252-288Rf, 272-310Fl, 286-316119, and 292-318120, are predicted using the improved GLDM with the diffuseness correction and the decay energies from WS4 and FRDM as inputs. Therefore, we conclude that the diffuseness effect should be embodied in the proximity energy. Moreover, increased application of neural network methods in nuclear reaction studies is encouraged.

A simple-to-use management approach to boost adaptive capacity of forests to global uncertainty

Given the uncertainty of global environmental changes, forest managers need reliable and science-based tools to support planning decisions. To evaluate the state of forests as well as the outcomes of new management practices aimed at fostering the adaptive capacity of forest ecosystems, methods and metrics for practitioners should be self-explanatory, based on easily-available data, and straightforward to use. Here, we present and apply the functional network approach, a trait-based approach that scales-up from species functional traits to community-level functional diversity and from stands to landscape-level functional connectivity, to guide sustainable forest management when faced with global change. In the functional network approach, (1) tree and shrub species are clustered into functional groups based on selected functional traits, (2) forest stands become the nodes of the network, and (3) functional traits can be exchanged between nodes according to species dispersal capacity via functional connectivity. We complemented the functional network approach with an assessment of stand-level vulnerability to natural disturbances. This new approach was applied to a mixed temperate forest landscape in south-eastern Canada to test four management scenarios varying in intensity (5–40% of the landscape area) and silvicultural strategy, including planting tree species from rare functional groups or harvesting tree species from predominant functional groups. Managed stands were ranked according to functional diversity and vulnerability to disturbances, and species were considered for planting based on their contribution to functional diversity and level of vulnerability. We found that a species-rich forest may be a functionally poor ecosystem so its adaptive capacity and resilience may be strongly compromised in the face of high global uncertainty. In addition, both functional diversity and connectivity increased with more intense management, and when functionally rare species were planted. By adopting the functional network approach, forest practitioners have a new simple-to-use tool to evaluate landscape-level functional diversity, vulnerability, and functional connectivity. This tool can be used to inform both plans for mitigating natural disturbances and strategies for enhancing overall ecosystem adaptive capacity to future environmental conditions and societal demands.

Energy Management of Grid Interconnected Multi-Microgrids Based on P2P Energy Exchange: A Data Driven Approach

Grid interconnected multi-microgrids provides potential benefits to the consumers, where the microgrids (MGs) equipped with distributed generators (DGs), energy storage systems (ESSs), and diesel generators. However, intermittency of DGs, high cost of ESSs, and depleting fossil fuels are the major challenges for the economic operation of interconnected multi-microgrids. One potential way to address these challenges is to develop an energy management strategy (EMS) for the grid interconnected multi-microgrids. This paper proposes an EMS to reduce consumer energy consumption cost (ECC) using fuzzy-based peer-to-peer (P2P) energy exchange algorithm with dynamic pricing. In this context, the MGs consumers load power demand (LPD) and DGs output behaviors are modeled using random vector functional link network approach to predict future time slot values. Then, a fuzzy-based P2P energy exchange algorithm is developed to enable the surplus energy transfer to grid and/or MGs with dynamic pricing. Furthermore, an ESS charging/discharging energy control and diesel generator turn on strategies are developed based on the MGs deficit power. Then, the MGs consumer LPD reduction strategy is implemented based on the consumer ECC margin and energy consumption index. Finally, an EMS is proposed that includes on demand-supply strategy and consumer energy consumption cost reduction strategy based on the future time slot values. The novelty of the proposed work lies within the energy management of grid interconnected multi-microgrids and the reduction of consumers ECC through surplus energy transfer to grid and/or MGs using fuzzy-based P2P energy exchange algorithm with dynamic pricing. Historical data are used to demonstrate the effectiveness of the proposed EMS for grid interconnected multi-microgrids.

Identification of candidate genes for reproductive traits in cattle using a functional interaction network approach

Reproduction is a key element in cattle production systems. Systems biology approaches, including those involving gene networks, have been applied to genetic dissection complex phenotypes in cattle. A set of 385 genes associated with reproductive traits in cattle were included in a protein-protein network analysis to identify and prioritize candidate genes related to phenotypic differences in cattle reproduction. Genes belonging to the ubiquitin family - Ubiquitin C ( Ubc , Gene ID: 444874) and Ubiquitin B ( Ubb , Gene ID: 281370) -had the highest probability of being associated with these traits in cattle. Both proteins were identified as important hubs in a protein-protein interaction network, each having 3,775 interactions of 3,856 possible. Resequencing of the Ubb gene coding region to evaluate the presence of SNPs in a discovery population identified the G/T (rs110366695) transversion. This causes emergence of a stop codon and a protein truncated by 287 aa. The allelic frequency distributions found in two beef cattle breeds highlight the promise of further research into the effects of protein truncation and the potential of these proteins as molecular markers for semen quality.

Modelling and Analysis of IoT Technology Using Neural Networks In Agriculture Environment

The rapid development of internet, cloud computing and sensor networks lead to develop and deploy the Internet of Things (IoT) which is a hot topic for the researchers. It has started to be used in various areas. Thus, agriculture is one of the most popular IoT research area. In agriculture environment, farming platform area is being a huge open structure and farmers must protect the crops from extreme weather conditions namely; wind speed/direction, precipitation, air temperature, solar radiations, and relative humidity etc. These extreme weather conditions effect crops and farms very significantly. But with the benefits of Internet of Things technologies, an agriculture business become more easy and efficient despite extreme weather conditions. This paper provides a model of smart agriculture environment using neural networks that helps the farmers to make more accurate predictions for the future according to weather conditions. This paper proposed a time-delay radial basis function (TDRBF) network approach to model temporal and sequential relationship between the various weather condition sensor readings from the agricultural environment. The performance of the acquired network model was analysed statistically and presented in this paper. As a result, the results of the neural network model show that it could be used to predict the desired weather condition sensor readings beforehand in order to increase the productivity in agricultural environment and also it is possible that by using such an intelligent learning system could provide a life-long learning for the changing weather conditions in the farming area over the years.

Gene Expression Correlates of the Cortical Network Underlying Sentence Processing.

A pivotal question in modern neuroscience is which genes regulate brain circuits that underlie cognitive functions. However, the field is still in its infancy. Here we report an integrated investigation of the high-level language network (i.e., sentence-processing network) in the human cerebral cortex, combining regional gene expression profiles, task fMRI, large-scale neuroimaging meta-analysis, and resting-state functional network approaches. We revealed reliable gene expression-functional network correlations using three different network definition strategies, and identified a consensus set of genes related to connectivity within the sentence-processing network. The genes involved showed enrichment for neural development and actin-related functions, as well as association signals with autism, which can involve disrupted language functioning. Our findings help elucidate the molecular basis of the brain's infrastructure for language. The integrative approach described here will be useful for studying other complex cognitive traits.

The functional complex network approach to foster forest resilience to global changes

Human impacts on Earth’s ecosystems have greatly intensified in the last decades. This is reflected in unexpected disturbance events, as well as new and increasing socio-economic demands, all of which are affecting the resilience of forest ecosystems worldwide and the provision of important ecosystem services. This Anthropocene era is forcing us to reconsider past and current forest management and silvicultural practices, and search for new ones that are more flexible and better at dealing with the increasing uncertainty brought about by these accelerating and cumulative global changes. Here, we briefly review the focus and limitations of past and current forest management and silvicultural practices mainly as developed in Europe and North America. We then discuss some recent promising concepts, such as managing forests as complex adaptive systems, and approaches based on resilience, functional diversity, assisted migration and multi-species plantations, to propose a novel approach to integrate the functionality of species-traits into a functional complex network approach as a flexible and multi-scale way to manage forests for the Anthropocene. This approach takes into consideration the high level of uncertainty associated with future environmental and societal changes. It relies on the quantification and dynamic monitoring of functional diversity and complex network indices to manage forests as a functional complex network. Using this novel approach, the most efficient forest management and silvicultural practices can be determined, as well as where, at what scale, and at what intensity landscape-scale resistance, resilience and adaptive capacity of forests to global changes can be improved.

Ahşap Kompozit Malzemelerin Mekanik ve Fiziksel Özelliklerine göre Tahmininde Radyal Temelli Fonksiyon Sinir Ağının Kullanımı

Knowing the mechanical and physical properties of a material is the most important criteria for engineers and designers interested in determining the intended use of the material. The prediction of wood composite materials based on their mechanical and physical properties plays an important role in their future application. In this study, radial basis function network approach was employed for prediction according to mechanical and physical properties of wood composite materials such as particleboard, fiberboard, oriented strand board and plywood, which have widespread use in the furniture industry and construction sector. Four physical and mechanical properties were used as the board density, bending strength, bending elastic modulus and tensile strength in the prediction of the wood composite materials. This study will assist wood composite users in the selection of wood composite materials that will provide the mechanical and physical properties determined in advance for any construction. Moreover, the present study will fill this gap in literature.

High-Throughput Functional Analysis Distinguishes Pathogenic, Nonpathogenic, and Compensatory Transcriptional Changes in Neurodegeneration.

Discriminating transcriptional changes that drive disease pathogenesis from nonpathogenic and compensatory responses is a daunting challenge. This is particularly true for neurodegenerative diseases, which affect the expression of thousands of genes in different brain regions at different disease stages. Here we integrate functional testing and network approaches to analyze previously reported transcriptional alterations in the brains of Huntington disease (HD) patients. We selected 312 genes whose expression is dysregulated both in HD patients and in HD mice and then replicated and/or antagonized each alteration in a Drosophila HD model. High-throughput behavioral testing in this model and controls revealed that transcriptional changes in synaptic biology and calcium signaling are compensatory, whereas alterations involving the actin cytoskeleton and inflammation drive disease. Knockdown of disease-driving genes in HD patient-derived cells lowered mutant Huntingtin levels and activated macroautophagy, suggesting a mechanism for mitigating pathogenesis. Our multilayered approach can thus untangle the wealth of information generated by transcriptomics and identify early therapeutic intervention points.

Estimating oil\u2013gas ratio for volatile oil and gas condensate reservoirs: artificial neural network, support vector machines and functional network approach

Laboratory experiment ideally, is the main method to obtain PVT properties of the oil and gas reservoir fluids. The alternative two methods widely used when laboratory experiments are not available are: equation of state (EOS) and empirical PVT correlations. The EOS requires lots of numerical computations based on identifying the full compositions of the reservoir fluids properties. The measurement and calculation of these properties are very expensive and time consuming. On the other hand, using of PVT correlations which are based on easily measured field data such as reservoir pressure and temperature, and gas and oil density is reliable and more economic. In this work, three artificial intelligence (AI) technique models were developed to predict the oil–gas ratio (Rv) for volatile oil and gas condensate reservoirs. Thirteen actual reservoir fluid samples (five volatile oils and eight gas condensates) covering a wide range of fluid behavior and characteristics were used. Whitson and Torp three parameters EOS were used to generate modified black oil (MBO) PVT properties that were used as a data set for model development. The MBO PVT data points were extracted for each sample using commercial PVT software at five different separator conditions. The nature of the input data was studied showing that data type is clustered. In addition, the correlations between the input parameters were checked. This preprocessed is helpful in selecting the best method to deal with the input parameters that will be fed to the developed models. According to this analysis and since the input parameters have different ranges, normalization of these parameters is vital to improve the accuracy of the models and to get the solution quickly and efficiently. Results showed that taking the log for the input parameters is the best among the other normalization techniques. The AI techniques that have been implemented in this research are; Artificial Neural Network (ANN) models, Functional Networks (FNs) and Support Vector Machines (SVMs). Models developed based on these techniques used 17,941 data points and a ratio of 70% for training, 15% for validation, and 15% for testing. To develop these models, three Matlab codes were written for each tool where the provided input data in excel format were read and prepressed before implementation. Results obtained using these techniques showed that the ANN model predicted Rv with an average square correlation coefficient of 0.9999 and an average relative error of 0.15% while FNs predicted Rv with an average correlation coefficient of 0.9635 and an average relative error of 27.6%. It was noted that SVMs gave the best results with an average correlation coefficient of 0.9990 and an average relative error of 0.12%. The results concluded that ANN and SVM accurately predicted such data since this type of data are clustered and these two models can handle this kind of data. The newly developed models depend only on easily obtainable parameters in the field and can have varied applications when typical lab PVT reports are not available.

Estimate of the Head Produced by Electrical Submersible Pumps on Gaseous Petroleum Fluids, A Radial Basis Function Network Approach

Estimate of the Head Produced by Electrical Submersible Pumps on Gaseous Petroleum Fluids, A Radial Basis Function Network Approach

Multi-Region Correlation Based Functional Brain Network for Disease Diagnosis and Cognitive States Detection

A functional brain network has attracted much attention due to its capability of characterizing the functional connectivity patterns of the brain. The existing methods for network construction usually rely on the conventional measures such as Pearson correlation to determine the pairwise similarity between each pair of brain regions, thus ignoring the global structure relationship and the information communication flow among different brain regions. To this end, this paper proposes a directional brain network construction method based on effective distance. Specifically, the effective distance can capture the hidden relevance pattern among all the brain regions and provide a directional functional network reflecting information propagation paths among the functional brain areas simultaneously. When estimating the probability of the direction and the strength of the connectivity between two regions, the structure information characterized by their neighbors is also considered in our method. The functional brain network produced by our method is more flexible in uncovering physiological mechanisms of the brain compared with the conventional undirected network. The experiments on two fMRI data analysis tasks, i.e., disease diagnosis and cognitive state detection, show that our method outperforms the conventional functional brain network approaches, including Pearson correlation, structural equation modeling, and sparse representation-based method.

Consistency of Regions of Interest as nodes of fMRI functional brain networks.

The functional network approach, where fMRI BOLD time series are mapped to networks depicting functional relationships between brain areas, has opened new insights into the function of the human brain. In this approach, the choice of network nodes is of crucial importance. One option is to consider fMRI voxels as nodes. This results in a large number of nodes, making network analysis and interpretation of results challenging. A common alternative is to use predefined clusters of anatomically close voxels, Regions of Interest (ROIs). This approach assumes that voxels within ROIs are functionally similar. Because these two approaches result in different network structures, it is crucial to understand what happens to network connectivity when moving from the voxel level to the ROI level. We show that the consistency of ROIs, defined as the mean Pearson correlation coefficient between the time series of their voxels, varies widely in resting-state experimental data. Therefore the assumption of similar voxel dynamics within each ROI does not generally hold. Further, the time series of low-consistency ROIs may be highly correlated, resulting in spurious links in ROI-level networks. Based on these results, we recommend that averaging BOLD signals over anatomically defined ROIs should be carefully considered.

An oblique elliptical basis function network approach for supervised learning applications

We propose a neural network architecture based on the oblique elliptical basis function for supervised learning problems. In classification, a category can be a disconnected or non-convex region involving several overlapping or disjoint sub-regions of the feature space. Other existing supervised learning methods may have the restriction that only allows decision regions to be convex. Our proposed method overcomes this restriction by employing a rotational self-constructing clustering algorithm to decompose the feature space into a collection of sub-regions which can then be combined to make up individual categories. An unseen instance is classified to a certain category if its similarity to the category exceeds a threshold. The whole framework fits in a five-layer network consisting of input, component-similarity, cluster-similarity, aggregation, and output layers. A similar idea also applies to solving regression problems. A parameter learning algorithm based on least squares estimation is used to derive the weights of the underlying network. Our approach can offer some advantages in practicality. Through the incorporation of rotation, data can be clustered more appropriately than by standard elliptical basis functions. Also, our approach is applicable to single-label classification, multi-label classification, as well as regression problems. A number of experiments are conducted to show the effectiveness of the proposed approach.