Small-scale Networks Research Articles

The Evolution of Systems Biology and Systems Medicine: From Mechanistic Models to Uncertainty Quantification.

Understanding interaction mechanisms within cells, tissues, and organisms is crucial for driving developments across biology and medicine. Mathematical modeling is an essential tool for simulating such biological systems. Building on experiments, mechanistic models are widely used to describe small-scale intracellular networks. The development of sequencing techniques and computational tools has recently enabled multiscale models. Combining such larger scale network modeling with mechanistic modeling provides us with an opportunity to reveal previously unknown disease mechanisms and pharmacological interventions. Here, we review systems biology models from mechanistic models to multiscale models that integrate multiple layers of cellular networks and discuss how they can be used to shed light on disease states and even wellness-related states. Additionally, we introduce several methods that increase the certainty and accuracy of model predictions. Thus, combining mechanistic models with emerging mathematical and computational techniques can provide us with increasingly powerful tools to understand disease states and inspire drug discoveries.

Personalized Cloud-Based sEMG-to-Haptic System to Enable Long-Distance Communication for Usher Syndrome

Abstract Usher Syndrome is a congenital disease that causes severe hearing and vision loss and is the leading cause of childhood deafblindness in the United States. Current assistive technologies are limited, expensive, and do not support long-distance communication. This paper presents a personalized, wearable, long-distance communication system for the deafblind. This system is cloud-based and presents a surface electromyography (sEMG) gesture classification system that uses personalized, small-scale Convolutional Neural Networks (CNNs) tailored to individual users, addressing the variability in muscle signals that hinders the adoption of sEMG-based systems. By creating user-specific sensor and gesture configurations, the system adapts to unique signal patterns, variations in electrode placement, and muscle geometries, making it highly robust to user-specific differences. It transmits real-time muscle activation data to a centralized server for model training, inference, and gesture recognition. Experimental results demonstrate that personalized models(~1 MB per model) significantly outperform cross-user models in classification accuracy, with an average improvement of 4.49% in validation accuracy over cross-user models in a 36-user dataset. By enabling low latency and minimal hardware requirements communication, this system is suitable for assistive communication technologies, including a novel sEMG-to-haptic sleeve that facilitates long-distance tactile communication for the deafblind. Moreover, the personalized model and cloud-based system approach is extensible beyond sEMG, offering a general framework for personalized sensor signal classification and paving the way for more accessible and effective solutions for the deafblind community and beyond.

A flexible and lightweight signcryption scheme for underwater wireless sensor networks

Underwater wireless sensor networks (UWSNs) are a new research area gaining popularity. It has several key applications for instance; marine monitoring, surveillance, environmental sensing, etc. However, It has several challenges including security, node mobility, limited bandwidth, and high error rates. Thus, to solve these issues, herein we propose a new lightweight Signcryption scheme for UWSNs. The proposed scheme effectively balances computational complexity and enhances the security of UWSNS. In contrast to the other state-of-the-art cryptographic schemes, the proposed scheme consists of a single combined operation of encryption and signing processes, which significantly improves its computational and communicational performance to ensure confidence when transmitting data. We performed the experimentation, and the experimental results show that the proposed scheme performs well compared to the state-of-the-art model. In addition, the experimental results revealed that the proposed scheme had a 40% less computational cost, 30% less energy consumption, and 25% less communication overhead than the state-of-the-art methods. This makes the proposed scheme highly appropriate for resource-scarce UWSNs. The proposed scheme also showed good scalability, where the performance could be sustained from a small-scale network of 50 nodes to a bandwidth of 200 nodes. Further, the proposed model also kept the security and latency low for the mobile nodes in an environment with high node mobility over the underwater terrain. In addition, the proposed method ensures flexibility and scalability by offering compatibility with diverse network structures and seamless integration with various cryptographic approaches, making it adaptable for dynamic underwater environments and broader applications such as IoT and smart city networks.

Construction of a small-scale relief shading neural network model based on the attention mechanism

ABSTRACT Relief shading is a primary technique for representing the three-dimensional effects of terrain on a two-dimensional plane. This study applies deep learning to generate small-scale Swiss-style relief shading maps. An attention module is defined to focus on key information in feature maps. Based on the characteristics of relief shading and digital elevation model (DEM) data, U-Net is adjusted and optimized, resulting in the design and construction of an end-to-end relief shading neural network model (Attention Hillshading U-Net, A-UNet) built on a limited training dataset. By learning the terrain-shaping patterns from Swiss-style shading maps, the model overcomes the challenges posed by high terrain complexity and insufficient representation of landform morphology in small-scale relief shading maps. The study further investigates the impact of hyperparameters on the performance of the model in generating small-scale relief shading maps. Based on the quantitative performance of the model under different hyperparameter settings and adaptability to lower-resolution DEMs, the optimal hyperparameters for the model are determined. Additionally, experimental comparisons of small-scale relief shading map generation using A-UNet and other network models show that, compared to U-Net and its variants, A-UNet demonstrates superior adaptability to different pixel sizes, better terrain simplification, and enhanced generalization to various landform types.

Optimal speed limit control for network mobility and safety: a twin-delayed deep deterministic policy gradient approach

Variable speed limit control (VSLC) has emerged as a promising approach for improving traffic safety and reducing congestion. However, local adjustment of VSLC may have broader impacts on the transportation network performance due to driver rerouting. This study proposes a deep reinforcement learning (DRL) controller based on twin-delayed deep deterministic policy gradient (TD3) algorithm to improve mobility and safety over a small-scale interconnected network considering rerouting behavior. The proposed DRL-based VSLC controller is designed to handle a large number of possible speed limits at each time step by utilizing a deep actor-critic framework. The study also experiments with different reward functions to characterize network mobility, safety, and traffic oscillation. Additionally, we investigate the sensitivity of the control algorithm across different traffic patterns, driving behavior, and VSLC locations, where the proposed TD3 algorithm demonstrated robustness and generalizability. Our findings indicate that implementing network-specific reward functions leads to improvements in traffic safety and mobility. Specifically, it results in a 3.84% enhancement in overall safety, as measured by time-to-collision metrics, and a 33.2% improvement in mobility by reducing total travel time compared to the scenario without VSL control. While comparable in safety performance, TD3 outperforms deep deterministic policy gradient (DDPG) algorithm by 15.1% in terms of mobility. This study contributes to the understanding of the impacts of VSLC on transportation networks and provides insights into effective ways of implementing VSLC to improve network mobility and safety.

Magmatic activity at the slowest spreading rates: insights from a high-resolution earthquake catalog obtained from Gakkel Ridge Deep (Arctic Ocean)

At the eastern end of Gakkel Ridge, Arctic Ocean, spreading rates drop below 5 mm/y near the termination of the active mid-ocean ridge in the Laptev Sea. A small-scale ocean bottom seismometer network deployed for one year at a volcanic center near Gakkel Ridge Deep in sea ice covered waters revealed abundant microseismicity despite the low spreading rate. In order to reveal spreading processes, we analyze a manually picked earthquake catalog refined by low-magnitude events detected by template matching. We attribute seismicity occurring randomly in time and space to tectonic stress release along the ridge. During short time periods of hours to days, seismicity is organized in time and densely clustered in space with signs of migration away from an aseismic area. In analogy to volcanic centers at Knipovich Ridge and in Iceland, we interpret the seismicity as signs of ongoing localized magmatism occurring even at the slowest spreading rates.

A self-training spiking superconducting neuromorphic architecture

Neuromorphic computing takes biological inspiration to the device level aiming to improve computational efficiency and capabilities. One of the major issues that arises is the training of neuromorphic hardware systems. Typically training algorithms require global information and are thus inefficient to implement directly in hardware. In this paper we describe a set of reinforcement learning based, local weight update rules and their implementation in superconducting hardware. Using SPICE circuit simulations, we implement a small-scale neural network with a learning time of order one nanosecond per update. This network can be trained to learn new functions simply by changing the target output for a given set of inputs, without the need for any external adjustments to the network. Further, this architecture does not require programing explicit weight values in the network, alleviating a critical challenge with analog hardware implementations of neural networks.

Biomimetic spider web sensor designed with memristive oscillators for location-resolved disturbance detection

This article introduces a memristor-coupled oscillatory network utilizing niobium dioxide (NbO2) memristors and a biomimetic spider web structure. It focuses on the dynamic behaviors of single oscillators and small-scale networks within this unique system, particularly emphasizing voltage, current, and frequency characteristics. By strategically applying step voltage signals on a 1 + 3 node single-layer bio-inspired spider network, a single disturbance or multiple disturbances were addressed under continuous external stimuli, with analyzing phase differences induced by disturbances at various locations within the network and systematically categorizing these phases to empower decision-making. These pattern differences enable precise location-resolved disturbance detection through eight encodable phase patterns and their corresponding phase-space trajectories, showcasing memristors' precision in dynamic control. Additionally, amplitude changes and phase relationships between oscillators can be visually represented through color-mapped voltage values. This work opens avenues for developing intelligent, adaptive systems, advancing neuromorphic computing, and intelligent system control, offering possibilities for artificial intelligence to process complex information.

System level network data and models attack cancer drug resistance.

Drug resistance is responsible for >90% of cancer related deaths. Cancer drug resistance is a system level network phenomenon covering the entire cell. Small-scale interactomes and signalling network models of drug resistance guide directed drug development. Recently, proteome-wide human interactome and signalling network data have become available, which have been extended by drug-target interactions, drug resistance-inducing mutations, as well as by several cancer and drug resistance-related multi-omics datasets. System level signalling network models have become available examining therapy resistance, performing in silico clinical trials, and conducting large, in silico drug combination screens. Drug resistance network data and models have become interoperable and reliable. These advances paved the road for building proteome-wide drug resistance models.

Multiscale Residual Weighted Classification Network for Human Activity Recognition in Microwave Radar.

Human activity recognition by radar sensors plays an important role in healthcare and smart homes. However, labeling a large number of radar datasets is difficult and time-consuming, and it is difficult for models trained on insufficient labeled data to obtain exact classification results. In this paper, we propose a multiscale residual weighted classification network with large-scale, medium-scale, and small-scale residual networks. Firstly, an MRW image encoder is used to extract salient feature representations from all time-Doppler images through contrastive learning. This can extract the representative vector of each image and also obtain the pre-training parameters of the MRW image encoder. During the pre-training process, large-scale residual networks, medium-scale residual networks, and small-scale residual networks are used to extract global information, texture information, and semantic information, respectively. Moreover, the time-channel weighting mechanism can allocate weights to important time and channel dimensions to achieve more effective extraction of feature information. The model parameters obtained from pre-training are frozen, and the classifier is added to the backend. Finally, the classifier is fine-tuned using a small amount of labeled data. In addition, we constructed a new dataset with eight dangerous activities. The proposed MRW-CN model was trained on this dataset and achieved a classification accuracy of 96.9%. We demonstrated that our method achieves state-of-the-art performance. The ablation analysis also demonstrated the role of multi-scale convolutional kernels and time-channel weighting mechanisms in classification.

Non-linear relationship between built environment and non-motorized travel efficiency under the traffic micro-circulation model.

The built environment is an important determinant of travel demand and mode choice. Studying the relationship between the built environment and transportation usage can support and assist traffic policy interventions. Previous studies often assumed that this relationship is linear; however, the impact of the built environment on non-motorized travel efficiency may be more complex than the typically modeled linear relationships. This paper focuses on the core area of Chengguan District in Lanzhou City, utilizing multi-source big data including POI, OpenStreetMap, street view images, and built environment data. Using ArcGIS spatial analysis tools combined with the Extreme Gradient Boosting (XGBoost) model, we analyze the non-linear influence mechanisms and threshold effects of the built environment on non-motorized travel efficiency and establish a ranking of the relative importance of all built environment factors. The results indicate that factors such as the branch road/street, land-use mix, land-use density, neighborhood entrance/exit density, bus station density, and dead-end-roads density are key influences on non-motorized travel efficiency. Additionally, based on the non-linear thresholds presented in the partial dependence plots for built environment factors, this paper proposes optimization strategies for small-scale road network patterns, mixed land use, and bus-friendly environments, providing effective threshold ranges and decision-making references for urban planning and traffic management.

A study on flame reconstruction in a supersonic combustor using deep learning

This study investigates the application of a low-order reconstruction method for image reconstruction of a scramjet combustor. In the encoding network, reconstruction performance was assessed by evaluating adjustments to sampling channel count and modifications to neural network architectures. Upsampling methods such as convolutional neural networks (CNNs), interlayer attention mechanisms, and pixel shuffle were tested in the decoder network. Furthermore, a parameter expansion strategy based on the enlargement of convolutional feature map channels was proposed and examined. The results were quantified by morphological and frequency domain analyses under tests with datasets of different equivalence ratios, suggesting the effectiveness of the scheme for flashback prediction. It was found that the reconstruction effect of 6-point sampling is close to that of continuous sampling (68 points), which is the most cost-effective among the tested schemes. By comparing different network structures, the method proposed in this paper achieves better reconstruction results than the large-parameter CNN network with a small-scale network structure.

Small-scale cross-layer fusion network for classification of diabetic retinopathy

Deep learning-based automatic classification of diabetic retinopathy (DR) helps to enhance the accuracy and efficiency of auxiliary diagnosis. This paper presents an improved residual network model for classifying DR into five different severity levels. First, the convolution in the first layer of the residual network was replaced with three smaller convolutions to reduce the computational load of the network. Second, to address the issue of inaccurate classification due to minimal differences between different severity levels, a mixed attention mechanism was introduced to make the model focus more on the crucial features of the lesions. Finally, to better extract the morphological features of the lesions in DR images, cross-layer fusion convolutions were used instead of the conventional residual structure. To validate the effectiveness of the improved model, it was applied to the Kaggle Blindness Detection competition dataset APTOS2019. The experimental results demonstrated that the proposed model achieved a classification accuracy of 97.75% and a Kappa value of 0.971 7 for the five DR severity levels. Compared to some existing models, this approach shows significant advantages in classification accuracy and performance.

Semantic-aware frame-event fusion based pattern recognition via large vision–language models

Semantic-aware frame-event fusion based pattern recognition via large vision–language models

Single and multi-threaded power flow algorithm for integrated transmission-distribution-residential networks

Single and multi-threaded power flow algorithm for integrated transmission-distribution-residential networks

Abnormal cascading dynamics in transportation networks based on Gaussian distribution of load

Abnormal cascading dynamics in transportation networks based on Gaussian distribution of load

Optimization of Network Performance in Complex Environments with Software Defined Networks

Software-defined networks (SDN) have emerged as a promising approach to address the limitations of conventional networks. Its architecture can be implemented using either a single controller or multiple controllers. Although a single controller is inadequate for managing networks, deploying multiple controllers introduces the challenge of controller placement (CPP) in a network environment. To address these issues, this study presents a Software Defined Networks-Fault-Tolerant Method (SDN-FTM) where, in the event of a network failure, the SDN controller automatically reroutes traffic through an alternate, pre-configured network path, thereby maintaining uninterrupted service. The proposed SDN-FTM was tested and evaluated in real-time using Mininet simulation tools on a real-life small scale network data from tracking unit department in Walter Sisulu University (WSU), with a focus on performance measures such as latency and throughput. From the result obtained, the proposed method produced throughput and latency on Ryu with 2.15m/s and 18408m/s respectively. Furthermore, the findings indicate that Ryu controllers generally outperform OpenFlow controllers in terms of throughput, while OpenFlow controllers exhibit lower latency. The proposed method demonstrates significant improvements in network management by providing a robust solution for maintaining high network availability and performance in the presence of faults

Local detouredness: A new phenomenon for modelling route choice and traffic assignment

This study introduces the novel concept of local detouredness, i.e. detours on subsections of a route, as a new phenomenon for understanding and modelling route choice. Traditionally, Stochastic User Equilibrium (SUE) traffic assignment models have been concerned with judging the attractiveness of a route by its total route cost. However, through empirical analysis we show that considering solely the global properties of a route is insufficient. We find that it is important to consider local detouredness both when determining realistic and tractable route choice sets and when determining route choice probabilities. For example, analysis of observed route choice data shows that route usage tends to decay with local detouredness, and that there is an apparent limit on the amount of local detouredness seen as acceptable. No existing models can account for this systematically and consistently, which is the motivation for the new route choice model proposed in this paper: the Bounded Choice Model with Local Detour Threshold (BCM-LDT). The BCM-LDT model incorporates the effect of local detouredness on route choice probability, and has an in-built mechanism that assigns zero probabilities to routes violating a bound on total route costs and/or a threshold on local detouredness. Thereby, the model consistently predicts which routes are used and unused. Moreover, the probability expression is closed-form and continuous. SUE conditions for the BCM-LDT are given, and solution existence is proven. Exploiting the special structure of the problem, a novel solution algorithm is proposed where flow averaging is integrated with a modified branch-and-bound method that iteratively column-generates all routes satisfying local and global bounds. Numerical experiments are conducted on small-scale and large-scale networks, establishing that equilibrated solutions can be found and demonstrating the influence of the BCM-LDT parameters on choice set size and flow allocation.

Analysis of the Spatial Distribution and Common Mode Error Correlation in a Small-Scale GNSS Network.

When analyzing GPS time series, common mode errors (CME) often obscure the actual crustal movement signals, leading to deviations in the velocity estimates of station coordinates. Therefore, mitigating the impact of CME on station positioning accuracy is crucial to ensuring the precision and reliability of GNSS time series. The current approach to separating CME mainly uses signal filtering methods to decompose the residuals of the observation network into multiple signals, from which the signals corresponding to CME are identified and separated. However, this method overlooks the spatial correlation of the stations. In this paper, we improved the Independent Component Analysis (ICA) method by introducing correlation coefficients as weighting factors, allowing for more accurate emphasis or attenuation of the contributions of the GNSS network's spatial distribution during the ICA process. The results show that the improved Weighted Independent Component Analysis (WICA) method can reduce the root mean square (RMS) of the coordinate time series by an average of 27.96%, 15.23%, and 28.33% in the E, N, and U components, respectively. Compared to the ICA method, considering the spatial distribution correlation of stations, the improved WICA method shows enhancements of 12.53%, 3.70%, and 8.97% in the E, N, and U directions, respectively. This demonstrates the effectiveness of the WICA method in separating CMEs and provides a new algorithmic approach for CME separation methods.

Microfluidics-A novel technique for high-quality sperm selection for greater ART outcomes.

Microfluidics represent a quality sperm selection technique. Human couples fail to conceive and this is so in a significant population of animals worldwide. Defects in male counterpart lead to failure of conception so are outcomes of assisted reproduction affected by quality of sperm. Microfluidics, deals with minute volumes (μL) of liquids run in small-scale microchannel networks in the form of laminar flow streamlines. Microfluidic sperm selection designs have been developed in chip formats, mimicking invivo situations. Here sperms are selected and analyzed based on motility and sperm behavioral properties. Compared to conventional sperm selection methods, this selection method enables to produce high-quality motile sperm cells possessing non-damaged or least damaged DNA, achieve greater success of insemination in bovines, and achieve enhanced pregnancy rates and live births in assisted reproduction-in vitro fertilization (IVF) and intracytoplasmic sperm injection (ICSI). Besides, the concentration of sperm available to oocyte can be controlled by regulating the flow rate in microfluidic chips. The challenges in this technology are commercialization of chips, development of fully functional species-specific microfluidic tools, limited number of studies available in literature, and need of thorough understanding in reproductive physiology of domestic animals. In conclusion, incorporation of microfluidic system in assisted reproduction for sperm selection may promise a great success in IVF and ICSI outcomes. Future prospectives are to make this technology more superior and need to modify chip designs which is cost effective and species specific and ready for commercialization. Comprehensive studies in animal species are needed to be carried out for wider application of microfluidic sperm selection in invitro procedures.