Bimodal Networks Research Articles

Bimodal machine learning model for unstable hips in infants: integration of radiographic images with automatically-generated clinical measurements

Bimodal convolutional neural networks (CNNs) are frequently combined with patient information or several medical images to enhance the diagnostic performance. However, the technologies that integrate automatically generated clinical measurements within the images are scarce. Hence, we developed a bimodal model that produced automatic algorithm for clinical measurement (aaCM) from radiographic images and integrated the model with CNNs. In this multicenter research project, the diagnostic performance of the model was investigated with 813 radiographic hip images of infants at risk of developmental dysplasia of the hips (232 and 581 images of unstable and stable hips, respectively), with the ground truth defined by provocative examinations. The results indicated that the accuracy of aaCM was equal or higher than that of specialists, and the bimodal model showed better diagnostic performance than LightGBM, XGBoost, SVM, and single CNN models. aaCM can provide expert’s knowledge in a high level, and our proposed bimodal model has better performance than the state-of-art models.

Projection transformation-based link prediction for possible collaboration connections in bimodal supply chain networks

Aiming at the problems of information disconnection and business interruption in supply chain networks caused by uncertainties such as trade wars and COVID-19, a projection-transformation-based model for predicting possible collaborative relationship links in bimodal supply chain networks is designed from the perspective of network science. The model first transforms the bimodal network structure of supply chain into a corresponding unimodal projection network by projection transformation; then screens the candidate collaborative links in the network; finally assigns weights to the similarity links according to different influencing factors, and calculates the possibility of potential collaborative links in the bimodal supply chain network by this. The experimental results show that the model can achieve higher quality prediction in real bimodal supply chain networks compared with other baseline link prediction models, which provides theoretical and methodological support for better formulation of business contingency plans and risk defense measures.

EBFF-YOLO: enhanced bimodal feature fusion network for UAV image object detection

EBFF-YOLO: enhanced bimodal feature fusion network for UAV image object detection

The Types of Water Conflicts in an Irrigation System in Northern Mexico: Conflict as a Negative Link in Social Network Analysis

We used social network analysis (SNA) to identify the types of water-related conflicts between the users and members of the institutional arena of the Rio Mayo Irrigation District (RMID) within the ancestral territory of the Yoreme Mayo indigenous group in Sonora, northeastern Mexico. We combined ethnography with an analysis and visualization of bimodal networks that consisted of 118 users and their connections to the institutional arena’s 30 identified social actors who influence water management. Using a clustering algorithm, we identified four types of conflicts: (1) disputes between small- and large-scale farmers over (i) irrigation water and (ii) payments for water rights and land rental; (2) the struggle by large-scale farmers against the upper level of the water hierarchy, to obtain more water; (3) struggles by rural indigenous women against water providers, to conserve indigenous vernacular systems of managing water for domestic use; and (4) a “conflict” that turned out to be merely a structural remnant of the algorithm. We conclude that land- and water-grabbing in the RMID mainly affect indigenous small-scale farmers and that the combination of SNA and a clustering algorithm can identify the types of natural resource-related conflicts that might go undetected by other methodologies. However, SNA should in some cases be accompanied by a qualitative methodology.

A novel bimodal feature fusion network-based deep learning model with intelligent fusion gate mechanism for short-term photovoltaic power point-interval forecasting

Under the goals of carbon neutrality and peak carbon emissions, photovoltaic (PV) power generation is widely valued for its clean and green characteristics. However, the uncertainty and randomness of PV power pose challenges to energy management. Therefore, this study proposed a novel bimodal feature fusion network-based deep learning model with an intelligent fusion gate mechanism for short-term photovoltaic power point-interval forecasting. First, a threshold-guided iNNE-based outlier detection and repair method is designed for preprocessing PV data. Second, a bimodal feature fusion network was proposed to extract global and local features from PV power sequences, and the environmental factors-based rime optimization algorithm with growth mutation strategy and humidity perception mechanism was devised to optimize model's hyperparameters. Additionally, a photovoltaic power interval prediction model with a volatility segmentation strategy was introduced. Finally, the effectiveness of the proposed model, algorithm, and strategies was validated using measured datasets. The results demonstrated that under various weather conditions, the proposed model achieved point prediction evaluation metrics with an R2 exceeding 98 % and a prediction interval evaluation metric with a Prediction Interval Coverage Probability of 85.07 %. The obtained outcomes contribute to providing a basis for decision-making in the scientific scheduling and management of PV power systems.

Joint Routing and Pricing Control in Bimodal Mixed Autonomy Networks with Elastic Demand and Three-Dimensional Passenger Macroscopic Fundamental Diagram

The interaction between mixed autonomy traffic and public transport vehicles competing for limited road space is a less explored area of research. To evaluate the traffic dynamics in bimodal networks, a three-dimensional (passenger) network fundamental diagram, known as 3D-NFD (3D-pNFD), can be estimated that relates the accumulation of cars (autonomous and human-driven) and buses to the network vehicular (passenger) travel production. In this study, we propose a 3D-pNFD-based congestion pricing scheme considering three vehicle classes of buses, system-optimal (SO) seeking connected and automated vehicles (CAVs), and user-equilibrium (UE) seeking human-driven vehicles (HVs). We develop an iterative tri-level modeling framework for mode choice, pricing, and route choice in a mixed autonomy network. The lower level generates mixed equilibrium traffic flow through an integrated mixed equilibrium simulation-based dynamic traffic assignment model and a transit assignment model. The mid-level finds the optimal toll rates through a 3D-pNFD feedback-based controller. A nested logit-based mode choice model is also applied to capture travelers’ preferences toward three available modes and incorporates elastic demand. To encourage CAVs to follow the SO routing mode, they are provided with a discount on the congestion toll whereas UE-seeking HVs are subject to full price toll. Buses are also entirely exempt from the toll. We explore three scenarios with different discount rates on SO-seeking CAVs to investigate the effect of the incentive plans on the mode choice behaviors of road users in the pricing zone. The performance of the proposed model is evaluated in a large-scale network in Melbourne, Australia.

A deep learning framework for the joint prediction of the SOH and RUL of lithium-ion batteries based on bimodal images

Accurately predicting the state of health (SOH) and remaining useful life (RUL) is significant for battery-powered electric devices. Since the images generated from raw cyclic data of the batteries can reveal more inherent battery degradation characteristics than raw cyclic data studied in most of previous studies, the bimodal images generated by two methods, such as images of curves and Gramian angular field (GAF), are effectively integrated into a unified deep learning framework to predict the health states of lithium-ion batteries. To this end, a bimodal fusion regression network (BFRN) is elaborately designed to jointly predict SOH and RUL of the battery, in which the features of bimodal images for the battery are fully extracted, interactively fused and aggregated by specific-designed network modules. Experiments on the public MIT/Stanford dataset indicate that the proposed method can achieve accurate joint state prediction for lithium-ion batteries, with the coefficient of determination (R2) for the SOH and RUL tasks are 0.98 and 0.93, respectively, which is superior to existing deep learning methods. Experiments on another public battery dataset demonstrate that it can be practical and generalized for the batteries with other chemistries.

Managing day-to-day traffic mobility and emission of bi-modal road network with period-to-period pricing and subsidy scheme

This study develops a mathematical optimization approach to manage the traffic mobility and carbon emission of a multimodal road network through period-to-period combined traffic pricing and subsidy scheme. The current approach considers interaction between traffic modes and explicitly formulates it into a general day-to-day traffic dynamics model, making it apply to a more general road network. In addition, the established optimization model takes both efficiency and environment into account the model objective, and allows for more practical and flexible settings on problem constraints or objectives. A constrained compass search algorithm is applied to solve the model with poor properties. In the end, numerical experiments are performed to demonstrate the effectiveness of the methodology. It is found that the constrained compass search algorithm shows desirable effectiveness and robustness, and the combined pricing and subsidy strategy is much more effective than a single strategy in improving the network mobility and reducing emission. We also find that the effectiveness of ticket discount is much lower than that of increasing frequency under a wide range of passengers’ value of time. This implies that a superior way of leveraging the money obtained from traffic congestion pricing would be subsiding the bus system for raising its departure frequency.

Bimodal semantic fusion prototypical network for few-shot classification

Few-shot classification learns from a small number of image samples to recognize unseen images. Recent few-shot learning exploits auxiliary text information, such as class labels and names, to obtain more discriminative class prototypes. However, most existing approaches rarely consider using text information as a clue to highlight important feature regions and do not consider feature alignment between prototypes and targets, leading to prototype ambiguity owing to information gaps. To address this issue, a prototype generator module was developed to perform interactions between the text knowledge of the class name and visual feature maps in the spatial and channel dimensions. This module learns how to assign mixture weights to essential regions of each sample feature to obtain informative prototypes. In addition, a feature refinement module was proposed to embed text information into query images without knowing their labels. It generates attention from concatenated features between query and text features through pairwise distance loss. To improve the alignment between the prototype and relevant targets, a prototype calibration module was designed to preserve the important features of the prototype by considering the interrelationships between the prototype and query features. Extensive experiments were conducted on five few-shot classification benchmarks, and the results demonstrated the superiority of the proposed method over state-of-the-art methods in 1-shot and 5-shot settings.

Macroscopic modeling of mixed bi-modal urban networks: A hybrid model of accumulation- and trip-based principles

Network-level traffic flow models either assume steady-state urban flows (i.e. accumulation-based models) or track the movement of all vehicles (i.e. trip-based models). The steady-state assumption present in the accumulation-based models may pose a challenge in light of the multi-modal nature of urban flows. It might be indeed a rough assumption for the flow of some transportation modes like buses, cruising-for-parking vehicles, taxis, and on-demand vehicles. Trip-based models address this concern, however, they need significant parameter calibration effort and are not computationally efficient, which substantially reduces the practicality of these models in real-world applications. Nevertheless, despite the critical importance of developing multi-modal traffic flow models, few attempts have been made to investigate these models in network macroscopic fundamental diagram (NMFD)-related literature. This paper bridges this gap by developing a hybrid network-level traffic flow model for mixed bi-modal (i.e. car and bus) networks. The present hybrid model reproduces the dynamics of car flows via accumulation-based model principles while tracking the movement of buses using the trip-based model. This effort also includes the development of a new FIFO-based entrance function to ensure different modes experience the same delay under saturated traffic conditions. Different numerical experiments are conducted to study the hybrid model performance and to compare it with that of accumulation-based and trip-based models in both steady-state and transition periods under different traffic conditions. Our observations reveal that the hybrid model simulates the dynamics of cars and buses by closely following the behavior of its components under free-flow conditions. The model also outperforms the accumulation-based model under saturated traffic conditions while being considerably less demanding than the trip-based model. A further investigation of the model performance is performed for networks with different bus shares in both free-flow and saturated traffic conditions, confirming the results of the initial numerical experiments. The hybrid model’s computational efficiency is demonstrated. The potential real-world applications of the hybrid model in development of bi-modal network-level simulation models, NMFD-based control strategies along with bus space allocation policies, public transport operation problems, modeling of cruising-for-parking vehicles, taxis, and on-demand vehicles, and modeling and application of autonomous modular vehicles are discussed and future research directions are highlighted.

A bimodal feature fusion convolutional neural network for detecting obstructive sleep apnea/hypopnea from nasal airflow and oximetry signals

The most prevalent sleep-disordered breathing condition is Obstructive Sleep Apnea (OSA), which has been linked to various health consequences, including cardiovascular disease (CVD) and even sudden death. Therefore, early detection of OSA can effectively help patients prevent the diseases induced by it. However, many existing methods have low accuracy in detecting hypopnea events or even ignore them altogether. According to the guidelines provided by the American Academy of Sleep Medicine (AASM), two modal signals, namely nasal pressure airflow and pulse oxygen saturation (SpO2), offer significant advantages in detecting OSA, particularly hypopnea events. Inspired by this notion, we propose a bimodal feature fusion CNN model that primarily comprises of a dual-branch CNN module and a feature fusion module for the classification of 10-second-long segments of nasal pressure airflow and SpO2. Additionally, an Efficient Channel Attention mechanism (ECA) is incorporated into the second module to adaptively weight feature map of each channel for improving classification accuracy. Furthermore, we design an OSA Severity Assessment Framework (OSAF) to aid physicians in effectively diagnosing OSA severity. The performance of both the bimodal feature fusion CNN model and OSAF is demonstrated to be excellent through per-segment and per-patient experimental results, based on the evaluation of our method using two real-world datasets consisting of polysomnography (PSG) recordings from 450 subjects.

Implementation of the mathematical model of interaction of passenger transport modes for sustainable economic development

As part of a research, the study of the level of solving the scientific problem of transport flow management in large cities was carried out as a component of the integrated information-intelligent transport system of the city. A significant amount of research on a number of important components of the problem has been identified, including the application of new approaches, methods and information technologies for planning and forecasting traffic flows, optimization of bimodal urban networks. The software implementation of a mathematical model to optimize the interaction of urban passenger transport, passenger transfer points and urban trains in major transportation hubs in terms of sustainable development and digitalization was proposed. A toolkit for the integrated interaction of city train, urban passenger transport and passenger transfer points in major cities has been implemented. As a result of the study, a high level of versatility of the proposed model and the possibility of its active practical application was determined.

Bimodal SegNet: Fused instance segmentation using events and RGB frames

Object segmentation enhances robotic grasping by aiding object identification. Complex environments and dynamic conditions pose challenges such as occlusion, low light conditions, motion blur and object size variance. To address these challenges, we propose a Bimodal SegNet that fuses two types of visual signals, event-based data and RGB frame data. The proposed Bimodal SegNet network has two distinct encoders — one for RGB signal input and another for Event signal input, in addition to an Atrous Pyramidal Feature Amplification module. Encoders capture and fuse the rich contextual information from different resolutions via a Cross-Domain Contextual Attention layer while the decoder obtains sharp object boundaries. The evaluation of the proposed method undertakes five unique image degradation challenges including occlusion, blur, brightness, trajectory and scale variance on the Event-based Segmentation (ESD) Dataset. The results show a 4%–6% MIOU score improvement over state-of-the-art methods in terms of mean intersection over the union and pixel accuracy. The source code, dataset and model are publicly available at: https://github.com/sanket0707/Bimodal-SegNet.

Chromogenic probe adhered porous polymer monolith as real-time solid-state sensor for the detection of ultra-trace toxic mercury ions

The escalating predicament of water pollution has spurred the development of new chromogenic materials for the efficient detection/screening of toxic mercuric (Hg2+) ions. In this study, we report a simple and efficient detection stratagem by infusing a chromogenic ion-receptor (BTDA), i.e., 4-(benzothiazol-2-yl)-N, N-dimethylaniline onto a structurally intertwined meso-/macro-pore polymer template for the target-specific sensing of ultra-trace Hg2+. The structural/surface features of the monolithic polymer template, prepared from glycidyl methacrylate (GMA) monomer crosslinked with ethylene glycol dimethacrylate (EGDMA), facilitate voluminous infusion and uniform decoration of ion-receptor molecules across the continuous porous poly(GMA-co-EGDMA) framework, resulting in a solid-state colorimetric sensory system. The bimodal polymer network's intriguing surface and structural morphology of the chromogenic sensor material are interpreted using scanning/transmission electron microscopy, X-ray diffraction, photoelectron spectroscopy, energy dispersive X-ray spectrometry, optical spectroscopy, surface area, porosity and thermal analysis. The proposed Hg2+ sensor offers a linear response range of 1–150 μg/L, with a detection and quantification limit of 0.29 and 0.97 μg/L, respectively. The poly(GMA-co-EGDMA)-BTDA sensor exhibits a quick ion-sensing response (40 s) with distinct color transitions from pastel yellow to olive as a function of increasing Hg2+ concentration. The matrix tolerance studies for the proposed sensory system reveal high selectivity for Hg2+, with a recovery of ≥99.2% in on-site environmental samples. The sensor material exhibits excellent data reproducibility and reliability up to seven cycles of reusability.

Exploring bimodal multi‐level networks: Network structure and dynamics driving herding effects and growth in livestreaming

AbstractThe majority of social network research in the IS field relies on assumptions that social networks are single‐level unified entities, disregarding the potential bimodal network structure with the coexistence of centralized and decentralized networks and overlooking the essential role of adjacent nodes as decision‐makers. By challenging these assumptions, we propose that both centralized and decentralized networks can coexist within multi‐level bimodal platforms via various role‐based subgroups with different types of decision‐makers. Livestreaming platforms, exemplifying the coexistence of multi‐level networks within a single digital ecosystem, have become increasingly popular in various industries. Drawing on social impact theory (SIT), we examine the role of information from host‐audience centralized and host–host decentralized networks in shaping subscription increment and herding effects. Using a panel dataset in livestreaming, we find that bidirectional ties in host–host networks strengthen fan acquisition and herding effect in the host‐audience decentralized network, with hosts of lower social status gaining more fans than those with higher status in bidirectional ties. Our study contributes to the understanding of social network structure, herding effect, SIT and livestreaming by problematizing assumptions and offering a contextual explanation of livestreaming. Moreover, our work provides practitioners with valuable insights into leveraging network effects for hosts' success in livestreaming.

A Multilayer Network Approach for the Bimodal Bus–Pedestrian Line Planning Problem

In this paper, we formulate and solve the urban line planning problem considering a multilayer representation of a bimodal transportation network. Classical formulations are usually constructed over a planar network, which implies the need to introduce several strong non-linearities in terms of frequencies when modeling transfer times. In the proposed network representation, each candidate line is stored in a specific layer and the passengers’ movements for each origin–destination pair are modelled considering a strategy subgraph, contributing to a sparse model formulation that guarantees feasibility and simplifies the assignment process. The methodology is first tested using the Mandl network, obtaining results that are comparable in terms of quality with the best metaheuristic approaches proposed in the scientific literature. With the aim of testing its applicability to large scenarios, the proposed approach is then used to design the main urban transit network of Seville, a large scenario with 141 nodes and 454 links, considering artificial unfavorable demand data. The reasonable computation time required to exactly solve the problem to optimality confirms the possibility of using the multilayer approach to deal with multimodal network design strategic problems.

Introducing the open biomedical map of science.

This article introduces work in progress to develop a new, open biomedical map of science (OBMS) using the PubMed citation database. The new science map represents bimodal network relationships between journals and medical subject heading (MeSH) descriptors, based on a journal's articles indexed in the MEDLINE component of PubMed. We review the current efforts to use PubMed data in science of science studies and science mapping. As part of the development process, we compare the journals indexed in PubMed with journals included in the 2011 UCSD map of science to establish a baseline of disciplinary coverage of PubMed for the period 2009-2019. Journal article frequency is analyzed to establish the minimum number of citations required by a journal for inclusion in a map of science. A prototype OBMS is presented, and we discuss the strengths and weaknesses of the OBMS, as well as the next steps for using and productizing this new open map for general and free usage.

Fully automated thyroid ultrasound screening utilizing multi-modality image and anatomical prior

There is a high prevalence of thyroid nodules in the general population. Early detection is essential for the treatment of malignant thyroid nodules. Ultrasound has the advantage of being non-invasive and radiation-free, and is sufficient for early diagnosis of malignant nodules. However, ultrasound image acquisition relies on manual manipulation of the probe by the sonographer, making it difficult to screen populations for malignant thyroid nodules. Robotic ultrasound systems (RUS) are expected to replace sonographers in ultrasound scanning and improve the standardization and reproducibility of ultrasound examinations. However, there is currently no RUS that can fully autonomously screen for thyroid nodules. In this paper, we propose a fully automated two-step search method that mimics a physician's thyroid scanning protocol. First, using the body surface structure observed by the RGBD camera, we use a bimodal detection network for the initial localization of the human neck. The bimodal detection network achieves an average accuracy of 0.986. Second, we designed a tracking strategy based on the anatomical prior of the human neck to navigate the probe for thyroid ultrasound acquisition. An network-based visual servoing method enables shadow prevention and target tracking to be performed uniformly. In vitro experiments demonstrated the effectiveness of the protocol.

A path-based incentive scheme toward de-carbonized trips in a bi-modal traffic network

A path-based incentive scheme toward de-carbonized trips in a bi-modal traffic network

Bimodal transit design with heterogeneous demand elasticity under different fare structures

The study develops a new optimisation model to design a bimodal transit system from a microeconomic view to maximise the profit of a transit agency considering heterogeneous demand elasticity and different fare structures. Bimodal transit network parameters are optimized to better serve passenger demand. An elastic demand function is devised to include various time components and incorporate flat, distance-based, and hybrid fares. A nested iterative procedure is developed to find a near-optimal solution. Numerical experiments reveal the following interesting findings. First, the increase in elasticity parameters has a knock-on effect on the financial performance, consequently leading to a net profit reduction. Second, a distance-based fare scheme brings in the least actual demand but makes the most profit, compared with the flat and hybrid fare schemes. Third, passengers prefer using a rail-bus system to a BRT-bus system, especially at a higher demand level.