Search

Over the past ten years, there has been a significant increase in computer network intrusions, partly due to a thriving black market for cybercrime and the availability of advanced tools for committing such breaches. The most effective method for stopping unwanted intrusions and identifying abnormal network behavioral patterns is an intrusion detection system (IDS). In IDS, transfer learning techniques are frequently employed. An ML-based IDS experiences problems with data imbalance and a greater false detection ratio due to a small training dataset. These ID systems can quickly and automatically recognize harmful threats. The network requires a complex security solution because dangerous threats constantly develop and appear. As a result, developing an efficient and intelligent ID system is a substantial scientific challenge. We suggested an effective ensemble strategy that improved the spotted hyena optimization algorithm (ISHO) and the honey badger algorithm (HBA) to address the data imbalance and overfitting problem. The dataset is balanced by increasing the number of data samples and the detection precision. The Squeeze-and-Excitation (SE)-Deep Residual Network 152 (SE-ResNet152) approach is utilized to remove the less critical features. Every iterative phase includes using a list of decision trees, which monitor the performance of the categorizer and prevent overfitting issues. We use the datasets UNSW-NB15, CSE-CIC IDS 2018, and CICIDS2019 to simulate and assess the model. Compared to other approaches, the proposed approach performs well on three datasets and obtains above 99% accuracy, precision, recall, and F-measure. [ABSTRACT FROM AUTHOR]

Cyclic vertex connectivity c κ and cyclic edge connectivity c λ are two important kinds of conditional connectivity, which reflect the number of vertices or edges that can be removed before the graph is disconnected and at least two components contain a cycle, respectively. They have important applications in various networks such as computer networks or biochemical networks. In addition, a fullerene is a special kind of molecule in chemistry. A classic fullerene graph is a 3-connected cubic planar graph with only pentagonal and hexagonal faces. (4, 5, 6)-fullerene graphs are atypical fullerene graphs which also contain 4-faces. In this paper, we prove that c κ = c λ for (4 , 5 , 6) -fullerene graphs except for four exceptional graphs with order less than 16. We also give O (ν) -algorithms to determine the cyclic vertex connectivity and the cyclic edge connectivity of (4 , 5 , 6) -fullerene graphs. [ABSTRACT FROM AUTHOR]

The computer network environment is very complex, and there are many factors that need to be considered in the process of network security evaluation. At the same time, various factors have complex nonlinear relationships. Neural networks are mathematical models that simulate the behavioral characteristics of animal neural networks. They process information by adjusting the connection relationships of internal nodes, and have a wide range of applications in solving complex nonlinear relationship problems. The computer network security evaluation is multiple attribute group decision making (MAGDM) problems. In this paper, based on projection measure and bidirectional projection measure, we shall introduce four forms projection models with q-rung orthopair fuzzy sets (q-ROFSs). Furthermore, combine projection measure and bidirectional projection measure with q-ROFSs, we develop four forms of projection models with q-ROFSs. Based on developed weighted projection measure models, the multiple attribute group decision making (MAGDM) model is established and all computing steps are simply depicted. Finally, a numerical example for computer network security evaluation is given to illustrate this new model and some comparisons are also conducted to verify advantages of the new built methods. [ABSTRACT FROM AUTHOR]

In understanding human behaviour, computers sometimes condense their analysis of human behaviour into an analysis of the state of movement of keypoints in the human body. Thus, the technique of human pose estimation provides a convenient means for machines to recognise people's behaviour. The lightweight pose estimation network enables computers to detect human poses in real-time. This paper proposes Lightweight HRNet, a bottom-up lightweight network for multi-person human pose estimation. The network is proposed based on the HRNet architecture and includes four network branches with different resolutions and two network stages. The network backbone uses the ShuffleNet model, which allows the network to be better used on smaller devices. Notably, Lightweight HRNet focuses on a problem with multi-resolution, multi-branch parallel networks: not all stages of the network contain information about the feature maps of all its branches. Therefore, we proposed the Channel Exchange Module (CEM), which improves the exchange of information between each stage of the network and each of its branches. Among the tasks of human pose estimation, the addition of CEM improved the network accuracy of Lightweight HRNet by 0.9% in the COCO2017 test-dev. Finally, the network was able to achieve 46.6% accuracy on the COCO2017 test-dev. This accuracy is superior in the study of bottom-up lightweight human pose estimation networks. [ABSTRACT FROM AUTHOR]

With the deepening of industrial technology, the monitoring of the thermodynamic state of complex equipment systems has become a key to ensuring production continuity and safety. The thermodynamic state not only reflects the immediate working performance of the equipment but is also decisive in preventing overheating failures. The application of real-time remote monitoring technology provides a new solution for equipment health management, significantly reducing unexpected downtime, preventing failures, thus improving production efficiency and equipment lifespan. However, existing research still shows limitations in real-time data analysis, diversity of equipment adaptability, and accurate fault prediction. This paper proposes three innovative algorithms for the real-time remote monitoring of the thermodynamic state of complex equipment systems, and a method for mining overheating early warning information. The first algorithm, based on reconstruction error, is suitable for equipment with a large amount of normal operation data, using machine learning technology to accurately simulate the normal state to identify anomalies. The second single-class monitoring algorithm, suitable for situations with only normal operating data, can effectively detect deviations from the normal thermodynamic parameters. The third algorithm, based on statistical quantities, uses the statistical characteristics of equipment operation data for fault warning. In addition, the paper explores the application of the Bucket Sorting Fpgrowth algorithm in the mining of overheating early warning information of the thermodynamic state, analyzing potential fault modes and association rules through efficient data mining technology. These methods not only enhance the applicability and predictive accuracy of monitoring algorithms but also provide valuable decision support for equipment managers. [ABSTRACT FROM AUTHOR]

In the information age, frequent information exchange has provided a breeding ground for the spread of computer viruses. The significant losses caused by computer virus attacks have long rung the alarm for information security. From academia to businesses, and even to government, everyone remains highly vigilant about information security. Researchers have put forward various approaches to combat computer viruses, involving innovative efforts in both the hardware and software aspects, as well as theoretical innovation and practical exploration. This article is dedicated to theoretical exploration, specifically investigating the stability of a computer virus model, known as SLBRS, from the perspective of optimal control. Firstly, a control system is introduced with the aim of minimizing the costs related to network detoxification and diminishing the percentage of computers impacted by the virus. Secondly, we employ the Pontryagin maximum principle to analyze the optimality of a control strategy for the proposed system. Thirdly, we validate the effectiveness of our theoretical analysis through numerical simulation. In conclusion, both theoretical analysis and numerical simulation reveal that the utilization of optimal control analysis to stabilize the SLBRS has been demonstrated to be advantageous in restoring contaminated computer network environments. [ABSTRACT FROM AUTHOR]

This study aims to build a wireless computer network for a large company or university to enhance mobility and allow university users to stay connected at any time or place, which is achieved by applying the Universal Interoperability for Microwave Access (WiMax) technology. WiMax is based on the 802.16 sets of standards and has the most efficient and advanced hardware capabilities to meet the demands of teachers and students to browse the web or download files quickly. OPNET Modeler version 14.5 was used to determine the quality of service parameters of WiMax. [ABSTRACT FROM AUTHOR]

This study aims to use the theory of iterative control algorithm to learn and extract the semantic structural features of large-scale network data by analyzing and exploring the semantic structural features of large-scale networks with the help of data visualization analysis methods. In addition, it conducts relevant research on the high-quality simplified representation of computer network graphs based on the effective extraction of structural features and combined with graph sampling techniques. An iterative learning control algorithm based on reference trajectory update is proposed for the tracking control problem of discrete linear control system output subject to non-repetitive perturbation. First, the controller is parametrically optimized by constructing a performance index function to track the system output quickly and accurately at the desired point of reference trajectory update. Second, when the system output is affected by a batch of non-repetitive perturbations, a new performance indicator function is further constructed by introducing a Lagrange multiplier algorithm to establish multi-objective performance indicators to optimize the robust iterative learning controller. Finally, the algorithm is applied to a computer network graph design system, and the simulation results verify the reasonableness and effectiveness of the algorithm. These results show that the suggested technique surpassed the existing approaches with accomplishments such as an average degree of 12.5%, a clustering coefficient of 65%, network efficiency of 91%, and higher modularity, community identification, and network embedding scores. [ABSTRACT FROM AUTHOR]

The popularity of computer network has provided great convenience for people's work and life, but it has also brought corresponding information security problems. It is very important to do a good job in computer network security evaluation. Conventional computer network security evaluation can be realized with the help of firewalls, antivirus software, etc., while in the face of complex computer network applications, it is necessary to adopt a security evaluation method with good operability and wider application range. The computer network security evaluation is viewed as multiple attribute decision-making (MADM) issue. In this paper, an extended probabilistic simplified neutrosophic number grey relational analysis (PSNN-GRA) method is established for computer network security evaluation. The PSNN-GRA method integrated with Criteria Importance Though Intercrieria Correlation (CRITIC) method in probabilistic simplified neutrosophic sets (PSNSs) circumstance is applied to rank the optional alternatives and a numerical example for computer network security evaluation is used to proof the newly proposed method's practicability along with the comparison with other methods. The results display that the approach is uncomplicated, valid and simple to compute. [ABSTRACT FROM AUTHOR]

Mobile governance (m-Governance) has emerged as a new paradigm for governance in many countries, including India. This study investigates the benefits and barriers of m-governance in the context of Jammu and Kashmir. The study used an analytical and documentary method to reach at conclusion. The findings suggest that m-governance has the potential to enhance citizen engagement and participation, increase transparency and accountability, and improve service delivery. The study also highlights several barriers that hinder the effective implementation of m-governance, including the lack of technological infrastructure and expertise, low literacy rates, and limited access to mobile devices and network connectivity, particularly in rural areas. Furthermore, the study identified concerns related to data privacy and security as a significant challenge to the adoption of m-governance. The study recommends that policymakers should take a holistic approach to m-governance by addressing the barriers and challenges while leveraging the benefits of mobile technology. The study recommends that the government should prioritize the establishment of technological infrastructure, providing digital literacy programs, and strengthening data protection laws to address citizens' privacy concerns. The study concludes that m-governance has the potential to transform the governance landscape in Jammu and Kashmir by improving transparency, accountability, and service delivery, but it requires a collaborative effort from policymakers, government officials, citizens, and private stakeholders to overcome the barriers and harness its full potential. [ABSTRACT FROM AUTHOR]

In this paper, snake optimization algorithm (SOA) is used to find the optimal gains of an enhanced controller for controlling congestion problem in computer networks. M-file and Simulink platform is adopted to evaluate the response of the active queue management (AQM) system, a comparison with two classical controllers is done, all tuned gains of controllers are obtained using SOA method and the fitness function chose to monitor the system performance is the integral time absolute error (ITAE). Transient analysis and robust analysis is used to show the proposed controller performance, two robustness tests are applied to the AQM system, one is done by varying the size of queue value in different period and the other test is done by changing the number of transmission control protocol (TCP) sessions with a value of ± 20% from its original value. The simulation results reflect a stable and robust behavior and best performance is appeared clearly to achieve the desired queue size without any noise or any transmission problems. [ABSTRACT FROM AUTHOR]

An optimal network refers to a computer or communication network designed, configured, and managed to maximize efficiency, performance, and effectiveness while minimizing cost and resource utilization. In a network design and management context, optimal typically implies achieving the best possible outcomes between various factors. This research investigated the use of fuzzy graph edge coloring for various fuzzy graph operations, and it focused on the efficacy and efficiency of the fuzzy network product using the minimal spanning tree and the chromatic index of the fuzzy network product. As a network made of nodes and vertices, measurement with vertices is a parameter for domination, and edge measurement is a parameter for edge coloring, so we used these two parameters in the algorithm. This paper aims to identify an optimal network that can be established using product outcomes. This study shows a way to find an optimal fuzzy network based on comparative optimal parameter domination and edge coloring, which can be elaborated with applications. An algorithm was generated using an optimal approach, which was subsequently implemented in the form of applications. [ABSTRACT FROM AUTHOR]

There are a significant number of scientific publications that use epidemic models to propagate malicious objects in a computer network. These models are based on Markovian models with a constant intensity of transitions, which does not correspond to real conditions, since the intensity of transitions changes due to the fact that after some time antivirus systems start to recognize malware. This paper proposes an original approach based on an epidemic model with variable infection intensity of hosts in a computer network. In the beginning, when the threat is not recognized, the malware spreads rapidly. After a certain period of time, the antivirus system recognizes the malicious code, which leads to a decrease in the infection intensity. Simulations have been done for different infection intensity and threat recognition. Demonstrated models account for the infection time of hosts in the computer network, latency phase, malware detection, and clearance from the system. [ABSTRACT FROM AUTHOR]

In recent years, image super-resolution (SR) has made remarkable progress in areas such as natural images or text images. However, in the field of digital wallchart image super-resolution, existing methods have failed to preserve the finer details of text regions while restoring graphics. To address this challenge, we present a new model called Real Text-SwinIR (RT-SwinIR), which employs a novel plug-and-play Attention-based Learned Text Loss (LTL) technique to enhance the architecture's ability to render clear text structure while preserving the clarity of graphics. To evaluate the effectiveness of our method, we have collected a dataset of digital wallcharts and subjected them to a two-order degradation process that simulates real-world damage, including creases and stains on wallcharts, as well as noise and blurriness caused by compression during computer network transmission. On the proposed dataset, RT-SwinIR achieves the best 0.58 on Learned Text Loss and 0.11 on LPIPS, reduced by an average of 41.4% and 35.3%, respectively. Experiments have shown that our method outperforms prior works in digital wallchart image super-resolution, indicating its superior visual perceptual performance. [ABSTRACT FROM AUTHOR]

The Internet of Things (IoT) faces many security and privacy risks due to the large number of devices accessing the network while providing convenience to the current society. At present, the management of IoT devices is centralized. All terminal devices are managed in a centralized manner, and the data accessing IoT devices can only be connected to the network with the permission of the centralized nodes. In this scenario, the increase in the amount of equipment can cause central node overload or single node failure. Moreover, flexible expansion requirements are difficult to achieve in such a centralized architecture. This paper proposes a safe and efficient IoT device recognition and management scheme based on blockchain and edge computing, DRMT. This scheme realizes feature extraction, clustering, and learning of IoT devices' traffic based on the characteristics of distributed deployment of edge servers. In this process, the recognition model can be continuously updated. The scheme also has an advantage that it is possible to enhance the management efficiency and scalability of the system by establishing a blockchain network between edge servers to share identification information and automate deployment security. This paper also verifies the scheme's effectiveness by building an experimental network and a blockchain system. The results showed that DRMT would help realize the effective management of large-scale IoT devices in smart cities. [ABSTRACT FROM AUTHOR]

With the dramatic increase in the number of mobile users and wireless devices accessing the network, the performance of fifth generation (5G) wireless communication systems has been severely challenged. Reconfigurable intelligent surface (RIS) has received much attention as one of the promising technologies for the sixth generation (6G) due to its ease of deployment, low power consumption, and low price. RIS is an electromagnetic metamaterial that serves to reconfigure the wireless environment by adjusting the phase, amplitude, and frequency of the wireless signal. To maximize channel transmission efficiency and improve the reliability of communication systems, the acquisition of channel state information (CSI) is essential. Therefore, an effective channel estimation method guarantees the achievement of excellent RIS performance. This survey presents a comprehensive study of existing channel estimation methods for RIS. Firstly, channel estimation methods in high and low frequency bands are overviewed and compared. We focus on channel estimation in the high frequency band and analyze the system model. Then, the comprehensive description of the different channel estimation methods is given, with a focus on the application of deep learning. Finally, we conclude the paper and provide an outlook on the future development of RIS channel estimation. [ABSTRACT FROM AUTHOR]

Summary: The Internet of Things (IoT) is becoming a reality, and one of the core elements to make this reality come true is machine‐to‐machine (M2M) communication. With the fast‐growing rate in which devices are being deployed, communication among them has become crucial to support the development of IoT applications. The Long‐Term Evolution‐Advanced (LTE‐A) is a potential access network for these M2M devices. However, the LTE‐A inherited characteristics from older cellular network standards, which were designed for human‐to‐human (H2H) and human‐to‐machine (H2M) communication. Accordingly, supporting M2M communication poses some challenges to LTE‐A, with a highlight of the congestion and overload problems in the radio access network (RAN) during the random access channel (RACH) procedure. Such a problem arises due to the large number of devices sending access‐request messages to the network and the limited number of resources to satisfy this new demand. In this paper, we introduce a solution to mitigate the impact of M2M communication in the LTE‐A network. Precisely, we model how to divide the random access resources into different types of devices as a bankruptcy problem. Then, we propose two solutions: (i) A game theory approach to formulate the bankruptcy problem as a transferable utility game, and (ii) an axiomatic method where some elements are considered for judging the amount of resources each class should receive. The simulation results show that our approaches present improvements in terms of energy efficiency, impact control of M2M over H2H accesses, and priority respect among the different classes of devices. [ABSTRACT FROM AUTHOR]

The study of the maximum and minimal characteristics of graphs is the focus of the significant field of mathematics known as extreme graph theory. Finding the biggest or smallest graphs that meet specified criteria is the main goal of this discipline. There are several applications of extremal graph theory in various fields, including computer science, physics, and chemistry. Some of the important applications include: Computer networking, social networking, chemistry and physics as well. Recently, in 2021 exponential multiplicative Zagreb indices were introduced. In generalization, we introduce the generalized form of exponential multiplicative Zagreb indices for α ∈ R + \ { 1 }. Furthermore, to see the behaviour of generalized first and second exponential Zagreb indices for α ∈ R + \ { 1 } , we used a transformation method. In term of the two newly developed generalized exponential multiplicative Zagreb indices, we will investigate the extremal bicyclic, uni-cyclic and trees graphs. Four graph transformations are used and some bounds are presented in terms of generalized exponential multiplicative Zagreb indices. [ABSTRACT FROM AUTHOR]

Middleboxes are widely used in modern networks for a variety of network functions in cybersecurity, performance enhancement, and monitoring. Middlebox policy enforcement is however complex and tedious with unreliable manual re-configuration of legacy routers. The existing solution on automated policy enforcement relies on software-defined networking and does not apply to the traditional non-SDN networks, which remain popular today in enterprise deployment and core networks. This paper proposes a new architecture based entirely on software-defined middleboxes (instead of using software-defined switches in the prior art) to enable dependable and automated policy enforcement in non-SDN networks whose routers forward packets based on traditional routing protocols that are not policy-sensitive. We present a hot-potato enforcement strategy, which is then enhanced with two optimizations for load-balanced policy enforcement among software-defined middleboxes. Next, we propose two additional optimizations that minimize total traffic and aggregate end-to-end delays subject to link capacity constraints. Further enhancements are made to relieve middlebox processing overhead, avoid packet fragmentation due to policy enforcement, recover from failures, and mitigate delay for time-sensitive applications. We evaluate the proposed architecture on a real-life campus network topology and two simulated topologies to demonstrate the superior performance of our load-balanced enforcement strategies. [ABSTRACT FROM AUTHOR]

Internet of Things (IoT) technology has permeated into all aspects of today's society and is playing an increasingly important role. Identity authentication is crucial for IoT devices to access the network, because the open wireless transmission environment of the IoT may suffer from various forms of network attacks. The asymmetry in the comprehensive capabilities of gateways and terminals in the IoT poses significant challenges to reliability and security. Traditional encryption-based identity authentication methods are difficult to apply to IoT terminals with limited capabilities due to high algorithm complexity and low computational efficiency. This paper explores physical layer identity identification based on channel state information (CSI) and proposes an intelligent identification method based on deep reinforcement learning (DRL). Specifically, by analyzing and extracting the features of the real received CSI information and a setting low-complexity state, as well as action and reward parameters for the deep neural network of deep reinforcement learning oriented to the scenario, we obtained an authentication method that can efficiently identify identities. The validation of the proposed method using collected CSI data demonstrates that it has good convergence properties. Compared with several existing machine-learning-based identity recognition methods, the proposed method has higher recognition accuracy. [ABSTRACT FROM AUTHOR]

The importance of network security has increased with the emergence of networked systems in contemporary computing, making it an essential aspect of protecting digital assets and safeguarding against cyber threats. The current security mechanisms, which rely on cryptographic keys, may be susceptible to a number of attacks, such as media access control (MAC) spoofing, which might provide unauthorized users access to network resources. This study introduces a new approach, namely a zero-trust security framework with quantum fingerprinting for devices accessing a network, that utilizes quantum technology to protect networks from security threats and intruders. The proposed architecture relies on quantum fingerprinting to authenticate devices trying to access the network, and it is built on the zero-trust security concept. The framework is intended to offer a thorough, multi-layered approach to network security that may change in response to evolving security risks and specifications. By protecting against MAC spoofing and other types of device impersonation, the adoption of quantum fingerprinting adds another degree of protection. The proposed framework may be used to construct a reliable and scalable network security solution in different network environments. [ABSTRACT FROM AUTHOR]

This paper presents a deep learning approach to detect malicious communication in a computer network. The intercepted communication is transformed into behavioral feature vectors that are reduced (using principal component analysis and stepwise selection methods) and normalized to create training and test sets. A feed-forward artificial neural network is then used as a classifier to determine the type of malicious communication. Three training algorithms were used to train the neural network: the Levenberg-Marquardt algorithm, Bayesian regularization, and the scaled conjugate gradient backpropagation algorithm. The proposed artificial neural network topology after reducing the size of the training and test sets achieves a correct classification probability of 81.5 % for each type of malicious communication and of 99.6 % (and better) for normal communication. [ABSTRACT FROM AUTHOR]

The history of computer networks is relatively well described in Western literature but some parts of the world have been neglected. This paper explores the first ways in which computer networks were used in Yugoslavia, since these are different from the modes used in the West or Russia, because the dissolution of the country -- mixed with its transition from communism to democracy and the wars for independence -- created an environment which allowed computer networks to be used in unprecedented ways. The paper uses a mix of historical method, computational methods for collecting and analysing USENET data, semi-structured interview, archival research, and qualitative online observation. The main findings show that access to Western technology and participation in academic networks enabled Yugoslavian STEM academia and hackers to use computer networks for the first computer networks' propaganda war. Slovenians, Croatians, and Serbians created electronic mailing lists through which they tried to manipulate international actors and to bond the diaspora for a common cause, and they additionally fought in USENET discussion groups by implementing trolling techniques. [ABSTRACT FROM AUTHOR]

Due to the strong correlation between symmetric frames, video signals have a high degree of temporal redundancy. Motion estimation techniques are computationally expensive and time-consuming processes used in symmetric video compression to reduce temporal redundancy. The block-matching technique is, on the other hand, the most popular and efficient of the different motion estimation and compensation techniques. Motion compensation based on the block-matching technique generally uses the minimization of either the mean square error (MSE) or mean absolute difference (MAD) in order to find the appropriate motion vector. This paper proposes to remove the highly temporally redundant information contained in each block of the video signal using the removing temporal redundancy (RTR) technique in order to improve the data rate and efficiency of the video signal. A comparison between the PSNR values of this technique and those of the JPEG video compression standard is made. As a result of its moderate memory and computation requirements, the algorithm was found to be suitable for mobile networks and embedded devices. Based on a detailed set of testing scenarios and the obtained results, it is evident that the RTR compression technique allowed a compression ratio of 22.71 and 95% loss in bit rate reduction while maintaining sufficient intact signal quality with minimized information loss. [ABSTRACT FROM AUTHOR]

Metal silicides are considered promising candidates for the replacement of graphite due to their larger capacity than graphite used in Li-ion batteries. In this work, a type of lithium silicide composite material consisting of LixSi, graphite (G), and porous carbon (PC) together with carbon coating treatment, denoted as (LS-G-PC)@C, was prepared by high-energy ball milling and subsequent pitch pyrolysis. This type of material is used as a pre-lithiation additive to improve the initial Coulombic efficiency (ICE) of Si-based anodes. The microstructural characteristic of (LS-G-PC)@C composite material was analyzed by x-ray diffraction and scanning electron microscopy. The electrochemical properties were evaluated by cyclic voltammetry, electrochemical impedance spectroscopy, and capacity cycling tests. It has been found that the irregular particles of LS compounds are uniformly dispersed on the graphite sheet, which constitutes an effective conductive network together with PC. The addition of a 5 wt. % (LS-G-PC)@C pre-lithiation additive makes the ICE of a low ICE silicon-based composite material increase by 16%. At a current density of 100 mA g−1, the discharge capacity retention rate of the silicon-based composite increased from 86.1% to 91% after the 19th cycle, showing good cycle stability. Further work is to add higher levels of our pre-lithiation additive in order to improve the ICE significantly. [ABSTRACT FROM AUTHOR]

Machine learning (ML) has become the de-facto approach for various scientific domains such as computer vision and natural language processing. Despite recent breakthroughs, machine learning has only made its way into the fundamental challenges in computer systems and networking recently. This article attempts to shed light on recent literature that appeals for machine learning-based solutions to traditional problems in computer systems and networking. To this end, we first introduce a taxonomy based on a set of major research problem domains. Then, we present a comprehensive review per domain, where we compare the traditional approaches against the machine learning-based ones. Finally, we discuss the general limitations of machine learning for computer systems and networking, including lack of training data, training overhead, real-time performance, and explainability, and reveal future research directions targeting these limitations. [ABSTRACT FROM AUTHOR]

The fundamental monetary innovation embedded into cryptocurrencies is accounting coordination. Decentralized management of digital money's accounting by a network of computers is achieved as a Nash equilibrium of a coordination game among the network's nodes: the so called miners. Equilibrium analysis demands allowing miners to secretly update their accounting, i.e., to privately build multiple blocks of transactions and to deviate from the longest chain rule. We formalize such reasoning by proposing an accounting coordination game inspired on the Bitcoin design. In particular, by proposing a model that explicitly tells apart mining costs related to energy consumption from those related to computational capacity, we are able to study how symmetric equilibrium existence depends on well known parameters, like the average time for updating accounting records and the rewards collected from mining (accounting) activities. It is shown that the (off-equilibrium) possibility of double spending makes the attractiveness of the equilibrium strategy a decreasing function of the average time for updating accounting records. • Cryptocurrencies' fundamental innovation is accounting coordination. • Decentralized digital money management is a Nash equilibrium game among miners. • Model separates energy consumption and computational capacity mining costs. • Double spending possibility makes equilibrium strategy less attractive. • Equilibrium existence depends on time for accounting records and mining rewards. [ABSTRACT FROM AUTHOR]

The continued increase in Internet traffic requires that routing algorithms make the best use of all available network resources. Most of the current deployed networks are not doing so due to their use of single path routing algorithms. In this work we propose the use of a multipath capable routing algorithm using Evolutionary Algorithms (EAs) that take into account all the traffic going over the network and the link capacities by leveraging the information available at the Software Defined Network (SDN) controller. The designed routing algorithm uses Per-Packet multipath routing to make the best use of the network's resources. Per-Packet multipath is known to have adverse affects when used with TCP, so we propose modifications to the Multipath TCP (MPTCP) protocol to overcome this. Network simulations are performed on a real world network model with 41 nodes and 60 bidirectional links. Results for the EA routing solution with the modified MPTCP protocol show a 29% increase in the total network Goodput, and a more than 50% average reduction in a flow's end-to-end delay, when compared to OSPF and standard TCP under the same network topology and flow request conditions. [ABSTRACT FROM AUTHOR]

In the current enterprise competition, the core of the management information system is the financial management information system. Building a more comprehensive and efficient financial management information system can effectively establish a more efficient innovative enterprise and promote the transformation and development of the enterprise. This paper first designs a set of financial management system templates, including general ledger, accounts receivable, and accounts payable. Second, according to the characteristics of wireless sensor network technology, this paper proposes a financial management system based on the wireless sensor network and designs a load balancing topology control algorithm (LHTCA algorithm), which balances the energy consumption of network nodes and helps to improve the network life cycle. Finally, the management system is tested and validated. The test results show that the financial management system can realize the electronicization of financial data and paperless vouchers, improve the efficiency of financial work, and promote the sharing and integration of resources. [ABSTRACT FROM AUTHOR]

This paper introduces a novel framework for identifying a group of intrusions in the context of the Internet of Things (IoT). It combines both deep learning and decomposition. A set of data is first collected and a recurrent neural network is used to estimate the different individual intrusions. These individual intrusions are then used to identify a group of outliers based on a decomposition strategy. As case studies, the proposed solutions have been experimentally evaluated using two computer network intrusion datasets, namely (1) IDS 2018, and (2) LUFlow. The results show the benefits of the proposed framework and clear superiority in comparison to the state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

Blockchain is a method of recording information that makes it not feasible for the system to be replaced, attacked, or manipulated. A blockchain is equipped with a notebook that copies and processes the various procedures across the network of computers participating in the blockchain. Digital signature algorithm is one of the cryptographic protocols used by the blockchain. In this work, we introduce a new digital signature scheme based on error correcting codes. In the scheme constructed on a [n, k, d]− code over q , which is d ≥ 2t + 1, and the size of the signature length is n − k. The signature verification is based on the bounded distance decoding of the code. Since the verification space is q n , the proposed scheme has an improved performance in terms of working in a wider space. [ABSTRACT FROM AUTHOR]

In recent years, network coding has received extensive attention and has been applied to various computer network systems, since it has been mathematically proven to enhance the network robustness and maximize the network throughput. However, it is well-known that network coding is extremely vulnerable to pollution attacks. Certificateless network coding scheme (CLNS) is a recently proposed mechanism to defend against pollution attacks for network coding, which avoids tedious management of certificates and key-escrow attack. Until now, only a few constructions were presented, and more ones should be given so as to enrich this field. In this paper, for the first time, we study the general construction of CLNS from certificateless public auditing protocol (CL-PAP), although the two areas seem to be quite different in their nature and are studied independently. Since there are many candidates of CL-PAPs, we can naturally obtain abundant constructions of CLNSs according to our systematic way. In addition, in order to show the power of the general construction, we also present a concrete implementation given a specific CL-PAP. The performance analysis and experimental results show that the implemented CLNS is competitive in the existing network coding schemes. [ABSTRACT FROM AUTHOR]

The human pose estimation is a significant issue that has been taken into consideration in the computer vision network for recent decades. It is a vital advance toward understanding individuals in videos and still images. In simple terms, a human pose estimation model takes in an image or video and estimates the position of a person's skeletal joints in either 2D or 3D space. Several studies on human posture estimation can be found in the literature, however, they center around a specific class; for instance, model-based methodologies or human movement investigation, and so on. Later, various Deep Learning (DL) algorithms came into existence to overcome the difficulties which were there in the earlier approaches. In this study, an exhaustive review of human pose estimation (HPE), including milestone work and recent advancements is carried out. This survey discusses the different two-dimensional (2D) and three-dimensional human (3D) pose estimation techniques along with their classical and deep learning approaches which provide the solution to the various computer vision problems. Moreover, the paper also considers the different deep learning models used in pose estimation, and the analysis of 2D and 3D datasets is done. Some of the evaluation metrics used for estimating human poses are also discussed here. By knowing the direction of the individuals, HPE opens a road for a few real-life applications some of which are talked about in this study. [ABSTRACT FROM AUTHOR]

A central tenet of network science states that the structure of the network influences processing. In this study of a phonological network of English words we asked: how does damage alter the network structure (Study 1)? How does the damaged structure influence lexical processing (Study 2)? How does the structure of the intact network "protect" processing with a less efficient algorithm (Study 3)? In Study 1, connections in the network were randomly removed to increasingly damage the network. Various measures showed the network remained well-connected (i.e., it is resilient to damage) until ~90% of the connections were removed. In Study 2, computer simulations examined the retrieval of a set of words. The performance of the model was positively correlated with naming accuracy by people with aphasia (PWA) on the Philadelphia Naming Test (PNT) across four types of aphasia. In Study 3, we demonstrated another way to model developmental or acquired disorders by manipulating how efficiently activation spread through the network. We found that the structure of the network "protects" word retrieval despite decreases in processing efficiency; words that are relatively easy to retrieve with efficient transmission of priming remain relatively easy to retrieve with less efficient transmission of priming. Cognitive network science and computer simulations may provide insight to a wide range of speech, language, hearing, and cognitive disorders. [ABSTRACT FROM AUTHOR]

The application of automation technology realizes the transformation of people's production and life-style, and also promotes the transformation of the system form of the network environment. The application of automation in the current network industry is increasing, especially the use of advanced methods and technologies for automatic control. The purpose of this paper is to realize the research on the network measurement and control system in the field of automation technology to promote the ecological development of the network automation process. This paper proposes the use of neural network technology in automation technology to guide the construction of computer network measurement and control systems, which is helpful to analyze and solve the objective problems of system imbalance and improper command output in system automation. The automatic network control system is constructed and optimized by referring to the principles and laws of the neural networks, and the automation of the measurement and control system in the network field is realized. In the test of the system, the results show that when the experimental parameter setting is the input flow value of the flowmeter 2.05 sccm, the output frequency of the inverter in the system jumps between 25 and 40 Hz respectively. The specific parameters of the experiment set the output frequency of the inverter to 50 Hz, and the input flow value of the flowmeter jumps between 2.05 sccm and 4.00 sccm. Therefore, analyzing the measurement and control system of network automation is undoubtedly crucial to the current road in the field of network automation. [ABSTRACT FROM AUTHOR]

Brain-inspired machine learning is gaining increasing consideration, particularly in computer vision. Several studies investigated the inclusion of top-down feedback connections in convolutional networks; however, it remains unclear how and when these connections are functionally helpful. Here we address this question in the context of object recognition under noisy conditions. We consider deep convolutional networks (CNNs) as models of feed-forward visual processing and implement Predictive Coding (PC) dynamics through feedback connections (predictive feedback) trained for reconstruction or classification of clean images. First, we show that the accuracy of the network implementing PC dynamics is significantly larger compared to its equivalent forward network. Importantly, to directly assess the computational role of predictive feedback in various experimental situations, we optimize and interpret the hyper-parameters controlling the network's recurrent dynamics. That is, we let the optimization process determine whether top-down connections and predictive coding dynamics are functionally beneficial. Across different model depths and architectures (3-layer CNN, ResNet18, and EfficientNetB0) and against various types of noise (CIFAR100-C), we find that the network increasingly relies on top-down predictions as the noise level increases; in deeper networks, this effect is most prominent at lower layers. All in all, our results provide novel insights relevant to Neuroscience by confirming the computational role of feedback connections in sensory systems, and to Machine Learning by revealing how these can improve the robustness of current vision models. [ABSTRACT FROM AUTHOR]

The Innovative Optical and Wireless Network (IOWN) proposed by NTT envisions a future of low-latency, high-quality, and high-speed communications, but making this vision a reality will require a rapid evolution of optical communication devices. In particular, given the increase in network connection devices driven by recent advances in the Internet of Things and the emergence of communication applications with high real-time characteristics, the power consumption and latency of the communications infrastructure have become major issues throughout the world. We talked with NTT Distinguished Researcher Yuta Ueda about "tunable light source by electric-field control" technology as a solution to these issues. [ABSTRACT FROM AUTHOR]

Broadcasting in a computer network is a method of transferring a message to all recipients simultaneously. It is common in this situation to use a tree with many leaves to perform the broadcast, as internal nodes have to forward the messages received, while leaves are only receptors. We consider the subjacent problem of, given a directed graph D , finding a spanning arborescence of D , if one exists, with the maximum number of leaves. In this paper, we concentrate on the class of rooted directed acyclic graphs, for which the problem is known to be MaxSNP-hard. A 2-approximation was previously known for this problem on this class of directed graphs. We improve on this result, presenting a 3 2 -approximation. We also adapt a result for the undirected case and derive an inapproximability result for the vertex-weighted version of Maximum Leaf Spanning Arborescence on rooted directed acyclic graphs. [ABSTRACT FROM AUTHOR]

Semantic image segmentation in computer networks is designed to determine the category to which each pixel in an image belongs. It is a basic computer vision task and has a very wide range of applications in practice. In recent years, semantic image segmentation algorithms in computer networks based on deep learning have attracted widespread attention due to their fast speed and high accuracy. However, due to the large number of downsampling layers in a deep learning model, the segmentation results are usually poor at the edge of an object, and there is currently no universal quantitative evaluation index to measure the performance of segmentation at the edge of an object. Solving these two problems is of great significance to semantic image segmentation algorithms in China. Based on traditional evaluation indicators, this paper proposes a region-based evaluation index to quantitatively measure the performance of segmentation at the edge of an object and proposes an improved loss function to improve model performance. The existing semantic image segmentation methods are summarized. This paper proposes regional-based evaluation indicators. Taking advantage of the particularity of semantic image segmentation tasks, this paper presents an efficient and accurate method for extracting the edges of objects. By defining the distance from pixels to the edges of objects, this paper proposes a fast algorithm for calculating the edge area. Based on this, three methods are proposed as well as an area-based evaluation indicator. The experimental results show that the accuracy of the loss function proposed in this paper, compared with that of the current mainstream cross-entropy loss function, is improved by 1% on the DeepLab model. For area-based evaluation indicators, a 4% accuracy improvement can be achieved, and on other segmentation models, there is also a significant improvement. [ABSTRACT FROM AUTHOR]

In the modern-day world, a large number of queuing systems have been used in a variety of applications. Their usages involve huge amounts of complex computation coupled with inter and intra communication. However, in the vast majority of these systems, the available capacity is limited. Owing to these limitations, servers in general are prone to failures from time to time. Open network queuing system problems with breakdowns and its alternative repair strategies vastly increasing in computer and communication networks, needs proper modeling to solve day to day applications. The performance modeling of a multi-node system has been determined in this work taking into consideration arrivals at different periods. Proper analysis has been carried out thereby producing amazing results. [ABSTRACT FROM AUTHOR]