Large Network Capacity Research Articles

Pruning networks at once via nuclear norm-based regularization and bi-level optimization

Most network pruning methods focus on identifying redundant channels from pre-trained models, which is inefficient due to its three-step process: pre-training, pruning and fine-tuning, and reconfiguration. In this paper, we propose a pruning-from-scratch framework that unifies these processes into a single approach. We introduce nuclear norm-based regularization to maintain the representational capacity of large networks during pruning. Combining this with MACs-based regularization enhances the performance of the pruned network at the target compression rate. Our bi-level optimization approach simultaneously improves pruning efficiency and representation capacity. Experimental results show that our method achieves 75.4% accuracy on ImageNet without a pre-trained network, using only 41% of the original model’s computational cost. It also attains 0.5% higher performance in compressing the SSD network for object detection. Furthermore, we analyze the effects of nuclear norm-based regularization.

A Bandwidth and Gain Enhanced Hexagonal Patch Antenna using Hexagonal Shape SRR

In the evolving digital era, the primary focus of the telecommunications industry is on the 5G network, expected to deliver high data rates, low latency, large network capacity, and improved connectivity. This article discusses efforts to adopt optimal frequencies for 5G, introducing techniques to enhance the characteristics of microstrip antennas using Double Negative (DNG) metamaterial properties. The hexagonal-shaped Split Ring Resonant (HSRR) metamaterial is considered a potential method to increase the bandwidth and gain of 5G antennas. Simulation of HSRR unit cells shows a positive impact on DNG characteristics. Meanwhile, the antenna design incorporating HSRR superstrate elements significantly increases gain to 4.47 dBi, and the implementation of HSRR structures on the groundplane results in a remarkable 368% increase in bandwidth compared to conventional antennas without metamaterial.

An optimization investigation of enhanced practicality for the OFH/PC scheme based PON monitoring system

We propose a discrete and average approach, focusing on the code set rather than individual codes, for the PON monitoring system based on the optical frequency hopping/periodic code scheme. The discrete and averaged codes are designed to support large-capacity network monitoring, particular for next-generation PONs, while preserving the original encoder structure of the PON monitoring system. The proposed approach discretizes and averages optical frequency hopping/periodic codes with small and large intervals, employing a modified greedy algorithm that mitigates falling into local optimality and an efficient backtracking algorithm, respectively. Our proposed algorithms demonstrate exceptional efficiency and performance, as exemplified by the modified greedy algorithm, which surpasses the exhaustive method by over 2 millionfold in terms of speed. This approach significantly reduces the more rigorously defined probability of multiple-customer interference and lowers the final recognition difficulty, enhancing the practicality of the PON monitoring system. Additionally, we develop a cost-effective model to analyze optimal system costs for discrete-averaged codes in the cost-sensitive PON market, facilitating the practical application of the PON monitoring system in engineering practice.

Dust detection and cleanliness assessment based on S-YOLOv5s for NPP reactor containment wall-climbing cleaning robot

NPP reactor containment dust can easily turn into radioactive dust, endangering staff health and the environment. However, the nuclear reactor containment wall-climbing cleaning robot cleans blindly without the ability to clean the dust in a timely and thoroughly. In this paper, ShuffleNetV2-YOLOv5s (S-YOLOv5s) model is proposed to solve the problem of wall-climbing robots unable to detect different categories of dust in time. The use of ShuffleNetV2 in the backbone of the network not only ensures a large number of characterized channels and a large network capacity, but also reduces the complexity of the model; SIoU is chosen for the loss function to improve the model accuracy. Then, planar cleaning index (PCI) is proposed by combining the results of S-YOLOv5s to evaluate whether the wall-climbing cleaning robot cleans thoroughly. Compared to other methods, PCI considers amount and area occupation of different classes of dust. The dust data set is collected to train the designed model, and the model size is reduced to 14 % of the original model, and the FPS is 7.313 higher than the original model. Especially when compared with the state-of-the-art lightweight methods, our model has smaller model size and higher recognition speed. Experimental results have shown that our dust detection and cleanliness assessment method can be used on a wall-climbing cleaning robot to clean dust in time and thoroughly.

АНАЛІЗ ПРОСУВАННЯ ТЕХНОЛОГІЇ 5G У СВІТІ ТА ОЧІКУВАННЯ ДЛЯ УКРАЇНИ

The article analyzes the promotion, advantages and assessment of the achievements of 5G technology in the world, the available results of the implementation of 5G in various sectors of the economy despite the problems with its rapid development. The growing needs for speed and bandwidth of data transmission, increasing the number of connected devices without loss of communication quality, reducing delays and increasing reliability in conducting remote operations in real time, the development of innovations such as the Internet of Things (IoT), augmented reality ( AR) and virtual reality (VR), autonomous vehicles and the industrial sector, in particular on industrial automation and "smart" factories, the use of high-performance sensors and real-time robotics. The advantages of 5G technology, characterized by high data transfer speed, low support (latency), large network capacity, and improved mobility, are given. Episodes of the use of 5G in the military field in real time are described, to instantly store and reproduce large volumes of video and graphics, smart cities that use 5G to support a large number of sensors and sensors in the city, to implement a variety of services, energy management, public transport monitoring. Considered, the relevance of using the 5G mobile network in Ukraine remains high. The necessary steps in Ukraine from the development of standards, the allocation of frequencies, the creation of infrastructure and the acquisition of the necessary number of devices that support 5G are considered. A forecast of expected results such as infrastructure expansion is provided; access to a wide range of frequencies, including low and high bands; the ability to resist cyber attacks from a wide range of sources; energy efficient; compatible with existing infrastructure and other communication protocols. It was concluded that the introduction of the 5G network as soon as possible will provide an impetus for Ukraine from a technical and economic point of view.

High-frequency signal transmission in a coplanar waveguide structure with different surface finishes

Continuous pursuits for higher data rate, larger network capacity, low-latency communication, and better energy efficiency have motivated the development of the fifth generation (5 G) mobile communication technologies in recent years. Under a high-frequency transmission, the alternating electric current (AC) tends to distribute to the outer of a conductor due to the so-called “skin effect”; therefore, the surface coatings of Cu interconnect becomes an indispensable factor of the signal transmission characteristics. The focus of this study is to deeply probe into the effect of surface coatings on the high-frequency signal transmission (1–100 GHz) of Cu interconnects. We investigated six different surface finishes over a coplanar waveguide (CPW) transmission line structure, including immersion tin (ImSn), immersion silver (ImAg), immersion gold (IG), electroless palladium/immersion gold (EPIG), immersion gold/electroless palladium/immersion gold (IGEPIG), and ultrathin-Ni(P)-type ENEPIG. The high-frequency signal performance of the CPW transmission line was analyzed through the finite element analysis (FEA) method by using a 3D electromagnetic simulation software. Furthermore, experimental measurements were conducted by using a vector network analyzer (VNA) to characterize the signal loss arising from different surface finishes, so as to validate the numerical simulation results. The FEA and VNA results showed that a noticeable current redistribution might be induced by a high conductivity/permeability of surface coating(s), i.e., ImSn and ultrathin-Ni(P)-type ENEPIG, which significantly increases the signal insertion loss at high frequencies. Thus, an appropriate surface coating over Cu interconnects was necessary for enhancing the high-frequency signal transmission performance.

Design of Dual-Band Microstrip Linear Array MIMO Antenna With U Slot For 5G Communication System

The development of 5G technology is expected to result in high data rate communication, low power consumption and larger network capacity. Microstrip antenna is an antenna that can support 5G technology because it can work at high frequencies but has the disadvantage of producing a small gain and narrow bandwidth. The use of array and MIMO methods can increase the gain value. The addition of the U slot method aims to increase bandwidth and can produce multi-frequency. In this study, the antenna was designed using an epoxy substrate (FR-4) with a rectangular U-slot patch arranged in a 4×2 MIMO array and fabricated. From the simulation results, the return loss parameter (S11) is -12.49 dB, (S12) is -88.17 dB, bandwidth is 610 MHz, gain is 15.70 dB, envelope correlation coefficient is 3.85 × 10-10. and diversity gain of 10 dB. From the fabrication results, two working frequencies are obtained, namely at a frequency of 3.2 GHz and 3.62 GHz with each return loss value (S11) of -25.96 dB and -29.22 dB, (S12) of -48.61 dB and -51.78 dB, bandwidth of 50 MHz. The independence of each antenna is indicated by the envelope correlation coefficient of 6.48 × 10-6 and 1.5 × 10-6, and a diversity gain of 10 dB. This antenna can be recommended as a receiving antenna in 5G communication systems.

Book recommendation and purchase of intelligent image recognition technology under the background of 5G environment

In addition to a more extreme network experience and larger network capacity, 5G can also be used to rapidly transmit massive global text data at higher transmission speeds and higher reliability than previous communication technologies, allowing more communication devices around the world to operate at a faster rate. The transmission speed is safe and reliable to connect with each other. The rapid development of image recognition technology will be more effective in improving the operational efficiency of various industries. At present, scholars have used 5G technology and image recognition technology in the field of book management. This paper designs a book image recognition recommendation scheme based on 5G technology, in order to improve the problems of inaccurate book sales targets and low book classification efficiency of merchants from various perspectives. The image recognition book recommendation system combined with 5G technology is mainly divided into two steps: image recognition and book recommendation. The ultra-high speed provided by 5G technology can greatly improve the speed and accuracy of image recognition. Significantly reduces program running time. This paper first analyzes the related concepts of 5G, image recognition and recommendation algorithm, then sorts out the book image recognition method, and then designs the book recommendation purchase method. Combined with 5G technology, the image recognition and recommended purchase strategy are optimized. Finally, an online questionnaire is used to investigate the merchants using this method. The survey results show that the merchants who use this identification and purchase recommendation method have better performance in book classification, book personality recommendation, customer loyalty and book sales rate have greatly improved.

A Review of Two Types of New Key Technologies of 6G

The increasing need of future 6G wireless communication of higher transmission rate, larger network capacity, higher energy efficiency has been calling for the development of new key technologies. Among them, the two most popular and promising technologies are new spectrum access technology and efficient wireless transmission technology. New spectrum access technology intends to achieve the utilization of more available spectrum resources with higher frequency and wider bandwidth so that it can highly improve the data transfer rate and expand the network capacity. It includes Terahertz communication technology and visible light communication technology. Efficient Wireless Transmission technology aims to make new breakthroughs in traditional signal transmission mode and achieve larger channel capacity so that network coverage and security can be improved, and signal transmission loss can be decreased. It contains IRS technology and Spatial multiplexing technology. Properties of each technology, such as principles, advantages, application scenarios, are discussed in this paper. In chapter 2, new spectrum access technology is introduced, and efficient wireless transmission technology is introduced in chapter 3.

Energy Efficiency Fairness of Active Reconfigurable Intelligent Surfaces-Aided Cell-Free Network

Reconfigurable intelligent surface (RIS) has been widely recognized as a promising technique for future wireless communications. Benefiting from its ability to improve channel capacity with low cost and power consumption, the concept of RIS-aided cell-free network is proposed to break the bottleneck of current network architecture. However, the multiplicative fading effect (MFE) introduced by RIS prevents RIS-aided cell-free network from higher network capacity. To further increase the capacity of the RIS-aided cell-free network, in this paper, we propose the concept of active RIS-aided cell-free network, where the RIS is replaced by active RIS in traditional RIS-aided cell-free network. Moreover, we analyze the proposed network by investigating its energy-efficiency fairness (EEF). To elaborate, we formulate the EEF maximization problem in the active RIS-aided cell-free network, and propose a joint beamforming and resource allocation (JBRA) algorithm by exploiting alternating optimization (AO) and fractional programming (FP). Simulations results verify the proposed active RIS-aided cell-free network as well as the JBRA algorithm as an energy-efficient design for cell-free network with large network capacity.

Unrolled primal-dual networks for lensless cameras.

Conventional models for lensless imaging assume that each measurement results from convolving a given scene with a single experimentally measured point-spread function. These models fail to simulate lensless cameras truthfully, as these models do not account for optical aberrations or scenes with depth variations. Our work shows that learning a supervised primal-dual reconstruction method results in image quality matching state of the art in the literature without demanding a large network capacity. We show that embedding learnable forward and adjoint models improves the reconstruction quality of lensless images (+5dB PSNR) compared to works that assume a fixed point-spread function.

Guest Editorial: Quantum Communications and Networking

Quantum communication researchers have achieved significant progress during the recent decades and quantum networking has shown promise in terms of improving the overall functional benefits of the Internet and enabling applications with no counterpart in the classical world. It is a break-through technology towards the unimaginable future. In a quantum network, the source and destination may be connected by quantum repeaters/routers for facilitating qubit transmissions. The quantum network of the future is envisaged to pervade the entire globe, relying on terrestrial components, satellites, airplanes, ships and other vehicles. It is anticipated that it will support nearly unconditional security, super-computing power, large network capacity — even at high velocity — and privacy.

Human-Centered Efficient Explanation on Intrusion Detection Prediction

The methodology for constructing intrusion detection systems and improving existing systems is being actively studied in order to detect harmful data within large-capacity network data. The most common approach is to use AI systems to adapt to unanticipated threats and improve system performance. However, most studies aim to improve performance, and performance-oriented systems tend to be composed of black box models, whose internal working is complex. In the field of security control, analysts strive for interpretation and response based on information from given data, system prediction results, and knowledge. Consequently, performance-oriented systems suffer from a lack of interpretability owing to the lack of system prediction results and internal process information. The recent social climate also demands a responsible system rather than a performance-focused one. This research aims to ensure understanding and interpretation by providing interpretability for AI systems in multiple classification environments that can detect various attacks. In particular, the better the performance, the more complex and less transparent the model and the more limited the area that the analyst can understand, the lower the processing efficiency accordingly. The approach provided in this research is an intrusion detection methodology that uses FOS based on SHAP values to evaluate if the prediction result is suspicious and selects the optimal rule from the transparent model to improve the explanation.

The process mining method approach to analyze users’ behavior of internet in the Local Area Network of Sriwijaya University

The Sriwijaya University internet network management unit does not yet have a standard formulation for implementing Bandwidth Management & Bandwidth Allocation. To provide the best service, they apply the Best-Effort Service concept. As a result, it requires a relatively large network capacity and bandwidth provision so that it has an impact on costs. Therefore, it is necessary to know how users use internet bandwidth as the basic principle of Bandwidth Management & Bandwidth Allocation. This study has completed how to determine the behavior of internet users on the campus LAN as a reason to evaluate internet bandwidth usage. With the Process Mining method, process mapping has been carried out for all access to internet usage from all faculties. As a result, the factors that characterize and need to be considered in bandwidth management are obtained. In order of significance are Total Access Length, Average Variance, Number of User Case IDs, Number of Non-Academic Ports, Number of Academic Ports, Number of Access Frequency, Number of Events, and Number of Ports of Service.

A New Hybrid Prime Code for OCDMA Network Multimedia Applications

This paper presents a new family of spreading code sequences called hybrid prime code (HPC), to be used as source code for the optical code division multiple access (OCDMA) network for large network capacity. The network capacity directly depends on the number of available code sequences provided and their correlation properties. Therefore, the proposed HPC is designed based on combining two or more different code words belonging to two or more different prime numbers. This increases the number of code sequences generated. The code construction method utilized allows the generation of different code sets, each with different code length and weight, according to the number of prime numbers used. In addition, the incoherent pulse position modulation (PPM) OCDMA system is proposed based on the HPC code. Furthermore, the bit error rate (BER) performance analysis is introduced versus the received optical power and the number of active users. Moreover, the error vector magnitude (EVM) is calculated versus the optical signal-to-noise ratio. This work proves that using two prime numbers simultaneously generates far more codes than using prime numbers separately. It also achieved an OCDMA system capacity higher than the system that uses the optical orthogonal codes (OOCs), modified prime codes (MPCs) families, and two code families with separate simultaneously prime numbers, at a BER below 10−9 which is the optimum level.

Interdigitated photoconductive terahertz antenna for future wireless communications

AbstractRecently, the technology buzz on utilization of terahertz (THz) technology in beyond 5G and 6G communication is growing due to the demands for large network capacity, bandwidth, and ultrahigh data rates. The THz frequencies are prudent for short‐range future wireless communication systems as they provide extraordinary channel capacity with data rates from few Gb/s to Tb/s due to its ultra‐wide spectrum bandwidth. However, there exists many challenges in designing devices that operate under THz frequencies. The photo‐conductive antenna (PCA) is one of the crucial components that support realization of ultrafast wireless THz communications. In this paper, investigations on photoconductive antennas with interdigitated electrodes (IDEs) have been presented for THz communications with an equivalent circuit model for IPCA with corresponding solved expressions. The results show that the maximum THz field strength of 4.41 × 105 V/m is achievable by a 10 μm interdigitated teeth length IPCA with larger spectrum bandwidth of about ~8 THz. The antenna module makes the possibility of miniaturization of the THz sources and detectors for the emerging variety of wireless THz applications.

PON Monitoring Scheme Using Wavelength- Bandwidth Identification of a Single Fiber Bragg Grating

We propose and experimentally demonstrate a centralized PON monitoring scheme using the reflection spectrum of a single fiber Bragg grating. Each fiber Bragg grating used in the scheme adopts different central reflection wavelength or 3-dB reflection bandwidth. The unique reflection spectrum is generated after each fiber Bragg grating used is interrogated by a broadband probe source. These generated reflection spectra are used to identify and distinguish the drop fiber links. The similarity analysis model is established to solve the problem of waveform superposition identification for different 3-dB reflection bandwidths with the same central reflection wavelength, which can further improve the network monitoring capacity. The proposed scheme provides a simple and effective monitoring solution for large-capacity network, especially for high-density network with small end-user distance difference.

Next generation optical wireless communication: a comprehensive review

Abstract Next generation wireless networks are the need of the hour with reliable, high bandwidth, low Bit Error Rate (BER), high Signal to Noise Ratio (SNR), large network capacity, etc. for a paradigm shift to all optical networks from the prevailing conventional electro optic network due to the various benefits of optical links such as enormous bandwidth and extremely low losses. This paper presents a primitive overview of the foregoing technologies and then move on to encapsulating the contemporary techniques to enhance the system performance. For this, preceding limitation and their respective improvement measures from literature of fiber communication and its integration with the next generation networks mainly based upon Radio over Fiber (RoF), Fiber to the Home (FTTH) and Free Space Optics (FSO) are discussed. The advancement in the domain of optical wireless communication utilizing various methodologies is summarized. Finally, we conclude by incorporating various cost reduction methodologies developed which may further be explored to make next generation networks more promising.

Development of the fourth generation radio network and forecasting of its coverage in the conditions of urban development

Here is an example of how the fourth generation of cellular networks is developing rapidly today. The traffic per subscriber is growing every month. Operators are forced to provide coverage and the necessary capacity by installing new base stations. Quality network planning can provide better network performance and reduce deployment and optimization costs. It is also important to use a planning and optimization tool to model network coverage and perform performance analysis. According to the results of many studies, the amount of data transmitted over wireless networks has been growing significantly recently. Buildings are obstacles to the signal over long distances, so for the same area in different types of terrain for quality coverage it is necessary to place a different number of base stations. In addition, it is necessary to take into account the peculiarities of the building, as signals from different base stations are an obstacle for each other. On the other hand, high population density requires a large network capacity to meet the needs for speed and number of simultaneously connected users. Traffic is projected to increase by 2024, due to the emergence of new video services and the growing popularity and involvement of the population in existing ones. LTE-Advanced provides the ability to deploy repeaters to increase network performance. In the context of cellular communication systems, an important aspect is radio network planning - the process of locating base stations, determining the frequency channels and radio parameters of a wireless communication system to provide sufficient coverage and connection capacity to ensure the required level of service quality. to the user. Coverage planning refers to a geographic area where the network must provide a signal with sufficient power to provide access to voice or packet services, and capacity planning determines the system’s ability to provide services to a given number of subscribers. The purpose of the article is to study the process of planning the fourth generation LTE network in terms of urban development, calculations and modeling of coverage.

Design of a Wireless Temperature and Humidity Monitoring System Based on ZigBee Technology

With the development of the Internet of Things (IOT), ZigBee is more and more widely used in the field of automatic monitoring. In this study, ZigBee wireless sensor network is developed and applied in the specific field of environmental temperature and humidity measurement and control. It builds a wireless sensor network based on ZigBee technology, highlighting the technical advantages of low power consumption, safety and reliability, large network capacity and excellent topology ability, to realize the dynamic collection, analysis and processing of relevant data.