Simple Network Research Articles

Energy expansion planning with a human evolutionary model

This study presents a novel method for planning the expansion of transmission lines and energy storage systems while considering the interconnectedness of electricity and gas networks. We developed a two-level stochastic planning model that addresses both the expansion of transmission and battery systems in the electrical grid and the behavior of the gas network. This research explores the challenges and effects of integrating high levels of renewable energy sources while ensuring security within both networks. Our model uses a stochastic mixed-integer non-linear programming approach. To solve this complex model, we applied the Human Evolutionary Model (HEM). We tested our approach on two case studies: a simple 6-node network and the more complex IEEE RTS 24-bus network for the electricity grid, combined with 5-node and 10-node gas networks, respectively. The results demonstrate the effectiveness of our model, particularly in scenarios where connections in the power and gas networks are disrupted, preventing load shedding even when integrated network connections are cut.

StarCAN-PFD: An Efficient and Simplified Multi-Scale Feature Detection Network for Small Objects in Complex Scenarios

Small object detection in traffic sign applications often faces challenges like complex backgrounds, blurry samples, and multi-scale variations. Existing solutions tend to complicate the algorithms. In this study, we designed an efficient and simple algorithm network called StarCAN-PFD, based on the single-stage YOLOv8 framework, to accurately recognize small objects in complex scenarios. We proposed the StarCAN feature extraction network, which was enhanced with the Context Anchor Attention (CAA). We designed the Pyramid Focus and Diffusion Network (PFDNet) to address multi-scale information loss and developed the Detail-Enhanced Conv Shared Detect (DESDetect) module to improve the recognition of complex samples while keeping the network lightweight. Experiments on the CCTSDB dataset validated the effectiveness of each module. Compared to YOLOv8, our algorithm improved mAP@0.5 by 4%, reduced the model size to less than half, and demonstrated better performance on different traffic sign datasets. It excels at detecting small traffic sign targets in complex scenes, including challenging samples such as blurry, low-light night, occluded, and overexposed conditions, showcasing strong generalization ability.

A novel transfer learning model for the real-time concrete crack detection

The crack is an important index to evaluate the damage degree of concrete structure. While, the traditional algorithms of crack detection have complex operations and weak generalization. The performance of crack detection algorithms based on deep learning has been improved, but it also increases the complexity of network structure. Thus, this paper proposes a simplified real-time network for automatic detection of concrete cracks. Taking advantage of a novel transformer-based detector (DETR) architecture integrating receptive fields attention blocks and a feature assignment mechanism, the proposed network can achieve a model with more accurate detection of cracks. Analyzing the association between crack targets and receptive fields on feature layers, the receptive fields attention block is introduced into the backbone, focusing on the target receptive field features. In addition, a neck block is added to the encoder to fuse multi-scale features, with a new feature assignment mechanism assigning features to shallow layers, in order to detect cracks in the shallow features. Finally, given the effect of the inconsistent cracks size on the precision of the loss function, a novel adaptive loss function is applied to replace the loss in the original model. In this paper, the improved model is applied on the homemade crack dataset, and ablation study are done on the added modules to verify their effectiveness. Also, our model is compared with advanced models in cracks detection by using a TIDE toolbox. It is proven that the proposed model has a good effect on crack detection, and has better performance compared with state-of-the-art algorithms.

Hybrid CMOS-Memristor synapse circuits for implementing Ca ion-based plasticity model

Neuromorphic computing research is being actively pursued to address the challenges posed by the need for energy-efficient processing of big data. One of the promising approaches to tackle the challenges is the hardware implementation of spiking neural networks (SNNs) with bio-plausible learning rules. Numerous research works have been done to implement the SNN hardware with different synaptic plasticity rules to emulate human brain operations. While a standard spike-timing-dependent-plasticity (STDP) rule is emulated in many SNN hardware, the various STDP rules found in the biological brain have rarely been implemented in hardware. This study proposes a CMOS-memristor hybrid synapse circuit for the hardware implementation of a Ca ion-based plasticity model to emulate the various STDP curves. The memristor was adopted as a memory device in the CMOS synapse circuit because memristors have been identified as promising candidates for analog non-volatile memory devices in terms of energy efficiency and scalability. The circuit design was divided into four sub-blocks based on biological behavior, exploiting the non-volatile and analog state properties of memristors. The circuit was designed to vary weights using an H-bridge circuit structure and PWM modulation. The various STDP curves have been emulated in one CMOS-memristor hybrid circuit, and furthermore a simple neural network operation was demonstrated for associative learning such as Pavlovian conditioning. The proposed circuit is expected to facilitate large-scale operations for neuromorphic computing through its scale-up.

Anomaly detection based on system text logs of virtual network functions

In virtual network environments building secure and effective systems is crucial for its correct functioning, and so the anomaly detection task is at its core. To uncover and predict abnormalities in the behavior of a virtual machine, it is desirable to extract relevant information from system text logs. The main issue is that text is unstructured and symbolic data, and also very expensive to process. However, recent advances in deep learning have shown remarkable capabilities of handling such data. In this work, we propose using a simple LSTM recurrent network on top of a pre-trained Sentence-BERT, which encodes the system logs into fixed-length vectors. We trained the model in an unsupervised fashion to learn the likelihood of the represented sequences of logs. This way, the model can trigger a warning with an accuracy of 81% when a virtual machine generates an abnormal sequence. Our model approach is not only easy to train and computationally cheap, it also generalizes to the content of any input.

Neural coding of space by time.

The intertwining of space and time poses a significant scientific challenge, transcending disciplines from philosophy and physics to neuroscience. Deciphering neural coding, marked by its inherent spatial and temporal dimensions, has proven to be a complex task. In this paper, we present insights into temporal and spatial modes of neural coding and their intricate interplay, drawn from neuroscientific findings. We illustrate the conversion of a purely spatial input into the temporal form of a singular spike train, demonstrating storage, transmission to remote locations, and recall through spike bursts corresponding to Sharp Wave Ripples. Moreover, the converted temporal representation can be transformed back into a spatiotemporal pattern. The principles of the transformation process are illustrated using a simple feed-forward spiking neural network. The frequencies and phases of Subthreshold Membrane potential Oscillations play a pivotal role in this framework. The model offers insights into information multiplexing and phenomena such as stretching or compressing time of spike patterns.

CNN-LSTM for MFCC-based Speech Recognition on Smart Mirrors for Edge Computing Command

Smart mirrors are conventional mirrors that are augmented with embedded system capabilities to provide comfort and sophistication for users, including introducing the speech command function. However, existing research still applies the Google Speech API, which utilizes the cloud and provides sub-optimal processing time. Our research aim is to design speech recognition using Mel-frequency cepstral coefficients (MFCC) and convolutional neural network–long short-term memory (CNN-LSTM) to be applied to smart mirror edge devices for optimum processing time. Our first step was to download a synthetic speech recognition dataset consisting of waveform audio files (WAVs) from Kaggle, which included the utterances “left,” “right,” “yes,” “no,” “on,” and “off. ” We then designed speech recognition by involving Fourier transformation and low-pass filtering. We benchmark MFCC with linear predictive coding (LPC) because both are feature extraction methods on speech datasets. Then, we benchmarked CNN-LSTM with LSTM, simple recurrent neural network (RNN), and gated recurrent unit (GRU). Finally, we designed a smart mirror system complete with GUI and functions. The test results show that CNN-LSTM performs better than the three other methods with accuracy, precision, recall, and an f1-score of 0.92. The speech command with the best precision is "no," with a value of 0.940. Meanwhile, the command with the best recall is "off," with a value of 0.963. On the other hand, the speech command with the worst precision and recall is "other," with a value of 0.839. The contribution of this research is a smart mirror whose speech commands are carried out on the edge device with CNN-LSTM.

Of criminals and cancer: The importance of social bonds and innate morality on cellular societies

The current dogma in cancer biology contends that cancer is an identity problem: mutations in a cell's DNA cause it to “go rogue” and proliferate out of control. However, this largely ignores the role of cell-cell interaction and fails to explain phenomena such as cancer reversion, the existence of cancers without mutations, and foreign-body carcinogenesis. In this proof-of-concept paper, we draw on criminology to propose that cancer may alternatively be conceptualized as a relational problem: Although a cell's genetics is essential, the influence of its interaction with other cells is equally important in determining its phenotype. We create a simple agent-based network model of interactions among normal and cancer cells to demonstrate this idea. We find that both high mutation rates and low levels of connectivity among cells can promote oncogenesis. Viewing cancer as a breakdown in communication networks among cells in a tissue complements the gene-centric paradigm nicely and provides a novel perspective for understanding and treating cancer.

HYACINTH: HYdrogen And Carbon chemistry in the INTerstellar medium in Hydro simulations

Aims. We present a new sub-grid model, HYACINTH – HYdrogen And Carbon chemistry in the INTerstellar medium in Hydro simulations – for computing the non-equilibrium abundances of H2 and its carbon-based tracers, namely CO, C, and C+, in cosmological simulations of galaxy formation. Methods. The model accounts for the unresolved density structure in simulations using a variable probability distribution function of sub-grid densities and a temperature-density relation. Included is a simplified chemical network that has been tailored for hydrogen and carbon chemistry within molecular clouds and easily integrated into large-scale simulations with minimal computational overhead. As an example, we applied HYACINTH to a simulated galaxy at redshift z ~ 2.5 in post-processing and compared the resulting abundances with observations. Results. The chemical predictions from HYACINTH are in reasonable agreement with high-resolution molecular-cloud simulations at different metallicities. By post-processing a galaxy simulation with HYACINTH, we reproduced the H I − H2 transition as a function of the hydrogen column density NH for both Milky-Way-like and Large-Magellanic-Cloud-like conditions. We also matched the NCO versus NH2 relation inferred from absorption measurements towards Milky-Way molecular clouds, although most of our post-processed regions occupy the same region as (optically) dark molecular clouds in the NCO – NH2 plane. Column density maps reveal that CO is concentrated in the peaks of the H2 distribution, while atomic carbon more broadly traces the bulk of H2 in our post-processed galaxy. Based on both the column density maps and the surface density profiles oŕ the different gas species in the post-processed galaxy, we find that C+ maintains a substantially high surŕace density out to ~10 kpc as opposed to other components that exhibit a higher central concentration. This is similar to the extended [C II] emission ŕound in some recent observations at high redshifts.

3D positioning of Camellia oleifera fruit-grabbing points for robotic harvesting

Camellia oleifera is an oilseed crop with high economic value. The short optimum harvest period and high labour costs of C. oleifera harvesting have prompted research on intelligent robotic harvesting. This study focused on the determination of grabbing points for the robotic harvesting of C. oleifera fruits, providing a basis for the decision making of the fruit-picking robot. A relatively simple 2D convolutional neural network (CNN) and stereoscopic vision replaced the complex 3D CNN to realise the 3D positioning of the fruit. Apple datasets were used for the pretraining of the model and knowledge transfer, which shared a certain degree of similarity to C. oleifera fruit. In addition, a fully automatic coordinate conversion method has been proposed to transform the fruit position information in the image into its 3D position in the robot coordinate system. Results showed that the You Only Look Once (YOLO)v8x model trained using 1012 annotated samples achieved the highest performance for fruit detection, with mAP50 of 0.96 on the testing dataset. With knowledge transfer based on the apple datasets, YOLOv8x using few-shot learning realised a testing mAP50 of 0.95, reducing manual annotation. Moreover, the error in the 3D coordinate calculation was lower than 2.1 cm on the three axes. The proposed method provides the 3D coordinates of the grabbing point for the target fruit in the robot coordinate system, which can be transferred directly to the robot control system to execute fruit-picking actions. This dataset was published online to reproduce the results of this study.

Determining plastic slips in rate-independent crystal plasticity models through machine learning algorithms

Dislocation slip-based crystal plasticity models have been a great success in connecting the fundamental physics with the macroscopic deformation of crystalline materials. Pioneered by Taylor in his work on “plastic strain in metals” (Taylor, 1938), and further advanced by Bishop and Hill (1951a, 1951b), the Taylor–Bishop–Hill theory laid the foundation of today’s constitutive models on crystal plasticity. An intriguing part of those modeling is to determine the active slip systems—which system to be involved in and how much it contributes to the deformation. In this paper, we developed a machine learning-based algorithm to determine accurately and efficiently the active slip systems in crystal plasticity constitutive models. Applications to the common three polycrystalline metals, face-centered cubic (FCC) copper, body-centered cubic (BCC) α-iron, and hexagonal close-packed (HCP) AZ31B, demonstrate that even a simple neural network could give rise to accurate and efficient results in comparing with traditional routines. There seems to be plenty of space for further reducing the computation time and hence scaling up the simulating samples.

A low-profile frequency- and pattern-reconfigurable metantenna for UAV joint RadCom systems

To address the specific requirements of antennas in Unmanned Aerial Vehicle (UAV) joint radar-communication (RadCom) systems, a novel low-profile reconfigurable metantenna with the capability of frequency and pattern reconfiguration is proposed in this paper. The proposed antenna consists of a metasurface layer with 3 × 3 square unit cells and a simple feeding network with two pairs of PIN diodes. Specifically, the designed metantenna has a low profile of 0.064 λ0 (λ0 is the free space wavelength at 5.5 GHz). And measured results show that, for the broadside radiation mode, the −10 dB operating bandwidth is about 12.1 %, ranging from 5.05 to 5.7 GHz with a maximum gain of 8.9 dBi. For the conical radiation mode, the −10 dB operating bandwidth is about 21.9 %, ranging from 5.88 to 7.33 GHz with a maximum gain of 6.83 dBi. Given its excellent radiation performance, the metantenna designed for UAV joint RadCom systems holds significant research significance and value in the field of multifunctional reconfigurable antennas.

Link-area commutators in AdS3 area-networks

Random tensor networks (RTNs) have proved to be fruitful tools for modelling the AdS/CFT correspondence. Due to their flat entanglement spectra, when discussing a given boundary region R and its complement R¯\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$ \\overline{R} $$\\end{document}, standard RTNs are most analogous to fixed-area states of the bulk quantum gravity theory, in which quantum fluctuations have been suppressed for the area of the corresponding HRT surface. However, such RTNs have flat entanglement spectra for all choices of R,R¯\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$ \\overline{R} $$\\end{document}, while quantum fluctuations of multiple HRT-areas can be suppressed only when the corresponding HRT-area operators mutually commute. We probe the severity of such obstructions in pure AdS3 Einstein-Hilbert gravity by constructing networks whose links are codimension-2 extremal-surfaces and by explicitly computing semiclassical commutators of the associated link-areas. Since d = 3, codimension-2 extremal-surfaces are geodesics, and codimension-2 ‘areas’ are lengths. We find a simple 4-link network defined by an HRT surface and a Chen-Dong-Lewkowycz-Qi constrained HRT surface for which all link-areas commute. However, the algebra generated by the link-areas of more general networks tends to be non-Abelian. One such non-Abelian example is associated with entanglement-wedge cross sections and may be of more general interest.

Design and optimization of two-stage controller for three-phase multi-converter/multi-machine electric vehicle

Abstract Electric vehicles (EVs) cut greenhouse gas emissions and our use of non-renewable resources, making them more attractive. EVs have lower fuel and maintenance expenses than internal combustion engine automobiles. This study proposes a multi-converter/Multi‒Machine system with two induction motors (IM) that drive a pure EV’s rear wheels. EV two-stage controllers using a simple Adaline neural network (NN) regulate Field-Oriented regulate of a three-phase IM. To control IM speed, the first controller level is a hybrid proportional–integral (PI) with a robust integral sign of error (RISE) controller. Injection torque is controlled by PI‒adaline NN in the second controller step. The simple Adaline NN improves two-stage controller performance. The Multi-Verse Optimization algorithm found the ideal RISE parameter to improve EV drive system performance. A plug-in EV’s linear speed is controlled by the Electronic Differential Controller (EDC). It uses the driver’s reference speed and steering angle to set each driving wheel’s reference speed. EDC adjusts wheel speeds to enhance traction and stability during cornering, accelerating, and decelerating. Utilizing this information, the EDC can effectively distribute power and torque to the wheels, thereby enhancing vehicle handling and overall performance. Three distinct road scenarios and the designated driving route topology have been used to act and demonstrate the resistive forces that affected the EV while it was traveling down the road. By using Matlab (Simulink), EV’s roadworthiness and efficiency will be evaluated.

Symmetric silicon microring resonator optical crossbar array for accelerated inference and training in deep learning

Photonic integrated circuits are emerging as a promising platform for accelerating matrix multiplications in deep learning, leveraging the inherent parallel nature of light. Although various schemes have been proposed and demonstrated to realize such photonic matrix accelerators, the in situ training of artificial neural networks using photonic accelerators remains challenging due to the difficulty of direct on-chip backpropagation on a photonic chip. In this work, we propose a silicon microring resonator (MRR) optical crossbar array with a symmetric structure that allows for simple on-chip backpropagation, potentially enabling the acceleration of both the inference and training phases of deep learning. We demonstrate a 4×4 circuit on a Si-on-insulator platform and use it to perform inference tasks of a simple neural network for classifying iris flowers, achieving a classification accuracy of 93.3%. Subsequently, we train the neural network using simulated on-chip backpropagation and achieve an accuracy of 91.1% in the same inference task after training. Furthermore, we simulate a convolutional neural network for handwritten digit recognition, using a 9×9 MRR crossbar array to perform the convolution operations. This work contributes to the realization of compact and energy-efficient photonic accelerators for deep learning.

Detection and comparison of reversible shape transformations in responsive polymers using deep learning and knowledge transfer by identifying stimulus-triggering characteristic points

Responsive polymers can alter their properties or shape according to stimuli such as stress, light, among others. The stimuli may be strategically programmed at assigned triggering points in a structure using additive manufacturing, which enables controlled deformation that is crucial for reversible shape transformation. Understanding and controlling shape transformation holds significance in topology optimization, or generative design, among other applications, where a material may not be reduced by machining; it can instead be reversibly transformed to perform evolving functions. However, handling responsive polymers can be challenging, as they react to various stimuli. The present research introduces a contactless technique using deep classification to detect and measure shape changes in responsive polymers. The application of deep network in responsive structural element (characteristic points) detection has not been attempted before. The classification categorizes polymers according to the degree of shape change, which aids in the verification of selectively programmed stimulus-responsive properties. By correlating the output with trained data, accurate classifications were made regarding the degree of shape change. The shape changes were then compared with different deformation angles, lengths, or heights through a novel formula-based correlation. The classification helps reconfigure the material if the deformation is not within the desired range. The classification and comparison were performed with AlexNet, which possesses a simple architecture. An accuracy of 100% was achieved by fine-tuning the hyperparameters of the same network. The present work thus shows the possibility of combining multiple tasks more efficiently with less data and computational resources using simple network.

Reliability analysis for 5G industrial network with application and dynamic coupling

The analysis of reliability is vital in ensuring the operation of 5G industrial networks (5GIN). With 5GIN are no longer merely chains of physical components, they consist of different applications that are dynamically deployed on base platform. Such a sharing of infrastructure between applications complicates the fault logic and greatly impacts their operation. Current reliability analysis tends to treat system as static, fail to take applications and dynamic coupling into accounts. This paper proposes a model consisting of network evolution model of 5GIN (NEM5G) and reliability-based sensitivity analysis (SA). NEM5G depicts the interaction of physical components and applications, which provides a description of dynamic coupling within system and its effect on reliability. Furthermore, SA helps identify influential parameters within 5GIN to support reliability optimization. The simulation results show that, our model achieves steady-state reliability aligned with that of the Continuous Time Markov Chain (CTMC) model in a simplified intelligent optical network case. When facing complex steel processing scenario, simulation results illustrate the variation trend of 5GIN reliability, further presents an importance ranking of parameters and analyzes available design strategies.

Retraction Note: Simplified neural network for generalized least absolute deviation

Retraction Note: Simplified neural network for generalized least absolute deviation

Cascading failures on interdependent hypergraph

Scientists are aware of the importance of studying interdependent networks, as they represent real-world scenarios better than isolated networks, such as the interdependent communication and power networks. However, in real scenarios, higher-order interactions exist in these networks. Recent research has shown that higher-order interactions that cannot be reflected in simple networks (i.e., a network only has pairwise interaction) can be reflected through hypergraph. This paper proposes an interdependent hypergraph model that considers the dependencies of interlayer nodes. We studied the cascading failures in the hypergraph with different interlayer dependencies. Through theoretical analysis, we have determined the maximum attack intensity the network can withstand and how its robustness changes under different attack intensities. In completely interdependent hypergraph, the network becomes increasingly fragile as the attack intensity increases, and the final network size suddenly jumps to zero, indicating a first-order phase transition in the network. We conducted experiments on multiple artificially synthesized hypergraph. The experimental results indicate that our analytical solution is consistent with the simulated solution. These findings will help us better understand the impact of different topologies on network robustness in interdependent hypergraph, enabling us to take more effective measures to address potential network failures and attacks.

Enhanced Indoor Positioning Using RSSI and Time-Distributed Auto Encoder-Gated Recurrent Unit Model.

This study presents a novel approach to indoor positioning leveraging radio frequency identification (RFID) technology based on received signal strength indication (RSSI). The proposed methodology integrates Gaussian Kalman filtering for effective signal preprocessing and a time-distributed auto encoder-gated recurrent unit (TAE-GRU) model for precise location prediction. Addressing the prevalent challenges of low accuracy and extended localization times in current systems, the proposed method significantly enhances the preprocessing of RSSI data and effectively captures the temporal relationships inherent in the data. Experimental validation demonstrates that the proposed approach achieves a 75.9% improvement in localization accuracy over simple neural network methods and markedly enhances the speed of localization, thereby proving its practical applicability in real-world indoor localization scenarios.