Massive Networks Research Articles

Is Canada Moving towards a More Agile Regulatory Approval and Reimbursement Process with a Shifting Role for Real-World Evidence (RWE) for Oncology Drugs?

Canada is known to have a complex pathway for new drug approval and reimbursement, resulting in delayed access for patients with serious and life-threatening diseases, such as cancer. Several recent publications from key stakeholders, including patients, physicians and policymakers, highlight patient helplessness, physician frustrations and policymakers entangled in a massive network of bureaucracy unable to make headway. Several quantitative and qualitative assessments using time from regulatory approvals to successful reimbursements confirm long review times and high rejection rates for oncology drugs, especially those receiving conditional approvals. A consensus forum of 18 Canadian oncology clinicians recently voiced frustration with the process and inability to deliver guideline-supported efficacious therapies to their patients. This manuscript compares data extracted from publicly available data sources from 2019 to June 2024 to previous publications. Methods: Public databases from Health Canada, the Canadian Agency for Drugs and Technologies in Health (CADTH), which is in the process of changing to Canada's Drug Agency, and the pan-Canadian Pharmaceutical Alliance (pCPA) were reviewed and the data collected were analyzed with descriptive statistics. Results: From the data, three trends emerge, (i) an increasing number of oncology drugs are receiving conditional approvals from Health Canada, (ii) the percentage of conditionally approved oncology drugs receiving positive reimbursement recommendations from CADTH is still low but appears to be improving, but delays in access are now contingent upon pCPA deciding whether to negotiate price and then the duration of any negotiation, and (iii) real-world evidence is no longer part of the decision-making for conditional approvals. A slight increase in the positive endorsement of RWE used to support CADTH recommendations was observed. Conclusions: The lack of timely access to oncology drugs hurts Canadian patients. While a small trend of improvement appears to be emerging, longer-term data collection is required to ensure sustained patient benefits.

Copula Approximate Bayesian Computation Using Distribution Random Forests

Ongoing modern computational advancements continue to make it easier to collect increasingly large and complex datasets, which can often only be realistically analyzed using models defined by intractable likelihood functions. This Stats invited feature article introduces and provides an extensive simulation study of a new approximate Bayesian computation (ABC) framework for estimating the posterior distribution and the maximum likelihood estimate (MLE) of the parameters of models defined by intractable likelihoods, that unifies and extends previous ABC methods proposed separately. This framework, copulaABCdrf, aims to accurately estimate and describe the possibly skewed and high-dimensional posterior distribution by a novel multivariate copula-based meta-t distribution based on univariate marginal posterior distributions that can be accurately estimated by distribution random forests (drf), while performing automatic summary statistics (covariates) selection, based on robustly estimated copula dependence parameters. The copulaABCdrf framework also provides a novel multivariate mode estimator to perform MLE and posterior mode estimation and an optional step to perform model selection from a given set of models using posterior probabilities estimated by drf. The posterior distribution estimation accuracy of the ABC framework is illustrated and compared with previous standard ABC methods through several simulation studies involving low- and high-dimensional models with computable posterior distributions, which are either unimodal, skewed, or multimodal; and exponential random graph and mechanistic network models, each defined by an intractable likelihood from which it is costly to simulate large network datasets. This paper also proposes and studies a new solution to the simulation cost problem in ABC involving the posterior estimation of parameters from datasets simulated from the given model that are smaller compared to the potentially large size of the dataset being analyzed. This proposal is motivated by the fact that, for many models defined by intractable likelihoods, such as the network models when they are applied to analyze massive networks, the repeated simulation of large datasets (networks) for posterior-based parameter estimation can be too computationally costly and vastly slow down or prohibit the use of standard ABC methods. The copulaABCdrf framework and standard ABC methods are further illustrated through analyses of large real-life networks of sizes ranging between 28,000 and 65.6 million nodes (between 3 million and 1.8 billion edges), including a large multilayer network with weighted directed edges. The results of the simulation studies show that, in settings where the true posterior distribution is not highly multimodal, copulaABCdrf usually produced similar point estimates from the posterior distribution for low-dimensional parametric models as previous ABC methods, but the copula-based method can produce more accurate estimates from the posterior distribution for high-dimensional models, and, in both dimensionality cases, usually produced more accurate estimates of univariate marginal posterior distributions of parameters. Also, posterior estimation accuracy was usually improved when pre-selecting the important summary statistics using drf compared to ABC employing no pre-selection of the subset of important summaries. For all ABC methods studied, accurate estimation of a highly multimodal posterior distribution was challenging. In light of the results of all the simulation studies, this article concludes by discussing how the copulaABCdrf framework can be improved for future research.

Artificial intelligence detection system based on multi-sensor and wireless communication

In today’s world, Internet technology and wireless communication technology are becoming more and more mature, which has brought massive network information resources to all sectors of society. At the same time, the phenomenon of data loss caused by illegal network intrusion is becoming more and more common. Therefore, it is necessary to identify and deal with them in combination with IDS (intrusion detection system). The problem of data processing is also very important. Enterprises can build a data management system according to their own needs, and use this system to process data. With the help of science and technology, AI (Artificial Intelligence) technology has become more mature and applied in many industries. Therefore, this paper proposed to build an AI IDS, and combined the deep RL (reinforcement learning) algorithm to analyze the performance of the system. This paper tested and analyzed the system from the aspects of precision and recall. The experimental results showed that the average precision of the five data sets was 94.76%, and the average recall rate was 91.4%. From the above data, combined with the algorithm in this paper, the precision and recall of the system have been significantly improved. This paper also conducted benchmark energy consumption comparison experiments for different cloud data management systems. The results showed that in terms of loading, the benchmark energy consumption of HBase was the lowest, which was 86KJ. In terms of query, the benchmark energy consumption of GridSQL was the lowest, which was 56KJ. It can be seen that different systems have their own advantages in the benchmark energy consumption of loading and query.

Computing Degree-Based Topological Descriptors of Certain Tessellations of Kekulenes Using M-Polynomial and Neighborhood M-Polynomial

Topological indices are well-known molecular descriptors that may be applied to any graph and to model specific molecular structures, utilized for property correlation in quantitative structure activity and property relationship (QSAR and QSPR) analyses. Strong methods for machine learning information and thermodynamic simulations of massive networks and nanomaterials can be facilitated by using topological indices. Kekulenes are a novel type of cycloarenes, arranged in doughnut-shaped cyclic benzene rings with riveting superaromaticity and other significant properties. The main aim of this paper is to ascertain the notable degree and the neighborhood degree sum-based indices through M-polynomials and neighborhood M-polynomials of certain types of tessellations of kekulenes. Then, a graphical comparison of the resulting indices is also performed.

Learning local cascading failure pattern from massive network failure data

Abstract This article proposes a novel multivariate point process regression model for a large-scale physically distributed network infrastructure with two failure modes, i.e. primary failures caused by the long-term usage and degradation of assets, and cascading failures triggered by primary failures in a short period. We exploit large-scale field pipe failure data from a UK-based water utility to support the rationale of considering the two failure modes. The two modes are not self-revealed in the data. To make the inference of the large-scale problem possible, we introduce a time window for cascading failures, based on which the likelihood of the pipe failure process can be decomposed into two parts, one for the primary failures and the other for the cascading failure processes modulated by the primary failure processes. The window length for cascading failures is treated as a tuning parameter, and determined through maximizing the likelihood based on all failure data. To illustrate the effectiveness of the model, two case studies are presented based on real data from the UK-based water utility. Interesting features of the cascading failures are identified from massive field pipe failure data. The results provide insights on advanced modelling and practical decision-making for both researchers and practitioners.

Deep reinforcement learning based controller placement and optimal edge selection in SDN-based multi-access edge computing environments

Multi-Access Edge Computing (MEC) can provide computility close to the clients to decrease response time and enhance Quality of Service (QoS). However, the complex wireless network consists of various network hardware facilities with different communication protocols and Application Programming Interface (API), which result in the MEC system's high running costs and low running efficiency. To this end, Software-defined networking (SDN) is applied to MEC, which can support access to massive network devices and provide flexible and efficient management. The reasonable SDN controller scheme is crucial to enhance the performance of SDN-assisted MEC. At First, we used the Convolutional Neural Networks (CNN)-Long Short-Term Memory (LSTM) model to predict the network traffic to calculate the load. Then, the optimization objective is formulated by ensuring the load balance and minimizing the system cost. Finally, the Deep Reinforcement Learning (DRL) algorithm is used to obtain the optimal value. Based on the controller placement algorithm ensuring the load balancing, the dynamical edge selection method based on the Channel State Information (CSI) is proposed to optimize the task offloading, and according to CSI, the strategy of task queue execution is designed. Then, the task offloading problem is modeled by using queuing theory. Finally, dynamical edge selection based on Lyapunov's optimization is introduced to get the model solution. In the experiment studies, the assessment method evaluated the performance of two sets of baseline algorithms, including SAPKM, the PSO, the K-means, the LADMA, the LATA, and the OAOP. Compared to the baseline algorithms, the proposed algorithms can effectively reduce the average communication delay and total system energy consumption and improve the utilization of the SDN controller.

Asynchronous Record Alignment of Network Flows for Incident Detection and Reconstruction

In today's interconnected digital landscape, the distribution of cyber threats presents a significant challenge to cyber security. Moreover, as of 2016, the amount of data in the world exceeds one zettabyte. Because of this, evidence-based network flow analytics is a critical component of modern network management and security. Problems such as anomalies in the network flow, cyber security incidents, alert generation, data pre-processing, network monitoring, network flow complexity, and data flow patterns become difficult to detect in massive network data flows. These specific problems can be addressed using Packet capture (PCAP). PCAP analysis is a standard network forensics process and investigation for assessing network behaviour and identifying anomalies. This work presents a method for analysing network flows for probable alignment of asynchronously recorded communications in heterogeneous networks. Using a proposed method for alignment, we can identify the relevant recordings aligned over two data streams for faster and more conclusive incident analysis. We use synthetic network incident scenarios for research experiments, detailing the generation of cyber event data and impact on cloud network traffic, followed by in-depth PCAP analysis. The automated cyber-attacks are simulated within a network infrastructure generating network flows in a PCAP format. Simulated cyber-attacks range from standard port scans, service scans, and specific scenarios like SQL injection, phishing, DoS or DDoS. We define analysis objectives and criteria for the in-depth PCAP analysis and alignment. The evidence gathered showcases valuable information about network data flow and its behaviour.

Analysis of factors influencing small-scale agricultural product prices from the perspective of the online public—a case study of China

In recent years, the high-frequency abnormal price fluctuations of small-scale agricultural products have been detrimental to market stability. The traditional method based on statistical data of production factors can no longer accurately predict abnormal price fluctuations. Therefore, this study takes scallions as an example and extracts the influencing factors of their prices based on the LDA-NLP-TVP-VAR model from massive network information, and analyzes the causes and changing characteristics of price fluctuations from four perspectives: market supply, economic environment and market sentiment, and attention. Initially, the study employs an LDA topic model to extract factors from online sentiment data over the past four years. Subsequently, using the SO-PMI algorithm to expand domain-specific lexicons and employing semantic and sentiment analysis with syntactic parsing, the study aims to improve the accuracy of sentiment quantification in text analysis. Furthermore, cointegration and Granger causality tests validate the significant impact of these factors on scallion price fluctuations, mitigating spurious regression issues. Finally, by employing a TVP-VAR model, the study compares the impulse responses and shock magnitudes of various factors in different time and spatial dimensions. It also delves into the mechanisms of heterogeneous impacts and trends in scallion prices, considering the corresponding socio-economic context and public sentiment events within specific time windows, thereby providing valuable decision-making insights for the healthy development of agricultural markets.

High Performance NMF based Intrusion Detection System for Big Data IoT Traffic

With the emergence of smart devices and the Internet of Things (IoT), millions of users connected to the network produce massive network traffic datasets. These vast datasets of network traffic, Big Data are challenging to store, deal with and analyse using a single computer. In this paper we developed parallel implementation using a High Performance Computer (HPC) for the Non-Negative Matrix Factorization technique as an engine for an Intrusion Detection System (HPC-NMF-IDS). The large IoT traffic datasets of order of millions samples are distributed evenly on all the computing cores for both storage and speedup purpose. The distribution of computing tasks involved in the Matrix Factorization takes into account the reduction of the communication cost between the computing cores. The experiments we conducted on the proposed HPC-IDS-NMF give better results than the traditional ML-based intrusion detection systems. We could train the HPC model with datasets of one million samples in only 31 seconds instead of the 40 minutes using one processor), that is a speed up of 87 times. Moreover, we have got an excellent detection accuracy rate of 98% for KDD dataset.

DomiRank Centrality reveals structural fragility of complex networks via node dominance

Determining the key elements of interconnected infrastructure and complex systems is paramount to ensure system functionality and integrity. This work quantifies the dominance of the networks’ nodes in their respective neighborhoods, introducing a centrality metric, DomiRank, that integrates local and global topological information via a tunable parameter. We present an analytical formula and an efficient parallelizable algorithm for DomiRank centrality, making it applicable to massive networks. From the networks’ structure and function perspective, nodes with high values of DomiRank highlight fragile neighborhoods whose integrity and functionality are highly dependent on those dominant nodes. Underscoring this relation between dominance and fragility, we show that DomiRank systematically outperforms other centrality metrics in generating targeted attacks that effectively compromise network structure and disrupt its functionality for synthetic and real-world topologies. Moreover, we show that DomiRank-based attacks inflict more enduring damage in the network, hindering its ability to rebound and, thus, impairing system resilience. DomiRank centrality capitalizes on the competition mechanism embedded in its definition to expose the fragility of networks, paving the way to design strategies to mitigate vulnerability and enhance the resilience of critical infrastructures.

ENERGY EFFICIENT OPERATION FOR NEXT GENERATION MASSIVE MIMO NETWORK

For the next generation of wireless networks, massive multiple-input, multiple-output (MIMO) is regarded as a potential technique. Base stations (BS) are provided with a relatively large number of antenna components in massive MIMO in order to increase spectral efficiency (SE) and energy efficiency (EE). Meanwhile, EE of BSs are becoming an increasingly important concern for communications operators in order to maintain profitability and reduce the overall negative impact on the environment and economic concerns for wireless network users. In this paper, an energy-aware, load-adaptive operation approach is proposed for massive MIMO for the next generation of wireless communication systems. Energy-aware, load-adaptive network operation has been identified as a promising method for improving the energy efficiency of telecommunication networks. Our research indicates that at optimal sumSE, fully load-adaptive massive MIMO may greatly increase network EE by up to 8.666%, 43.317%, and 69.367% for high, medium, and low load factors, respectively, when compared to traditional non-load-adaptive massive MIMO.

Single-Instruction-Multiple-Data Instruction-Set-Based Heat Ranking Optimization for Massive Network Flow

In order to cope with the massive scale of traffic and reduce the memory overhead of traffic statistics, the traffic statistics method based on the Sketch algorithm has become a research hotspot for traffic statistics. This paper studies the problem of the top-k flow statistics based on the Sketch algorithm and proposes a method to estimate the flow heat from massive network traffic using the Sketch algorithm and identify the kth flow with the highest heat by using a bitonic sort algorithm. In view of the performance difficulties of applying multiple hash functions in the implementation of the Sketch algorithm, the Single-Instruction-Multiple-Data (SIMD) instruction set is adopted to improve the performance of the Sketch algorithm so that SIMD instructions can process multiple fragments of data in a single step, implement multiple hash operations at the same time, compare and sort multiple flow tables at the same time. Thus, the throughput of the execution task is improved. Firstly, the elements of data flow are described and stored in the form of vectors, while the construction, analysis, and operation of data vectors are realized by SIMD instructions. Secondly, the multi-hash operation is simplified into a single vector operation, which reduces the CPU computing resource consumption of the Sketch algorithm. At the same time, the SIMD instruction set is used to optimize the parallel comparison operation of the flow table in a bitonic sort algorithm. Finally, the SIMD instruction set is used to optimize the functions in the Sketch algorithm and top-k sorting algorithm program, and the optimized code is tested and analyzed. The experimental results show that the time consumed by the advanced vector extensions (AVX)-instructions-optimized version has a significant reduction compared to the original version. When the length of KEY is 96 bytes, the instructions consumed by multiple hash functions account for less in the entire Sketch algorithm, and the time consumed by the optimized version of AVX is about 67.2% of that in the original version. As the length of KEY gradually increases to 256 bytes, the time consumed by the optimized version of AVX decreases to 53.8% of the original version. The simulation results show that the AVX optimization algorithm is effective in improving the measurement efficiency of network flow.

Learning massive interpretable gene regulatory networks of the human brain by merging Bayesian networks.

We present the Fast Greedy Equivalence Search (FGES)-Merge, a new method for learning the structure of gene regulatory networks via merging locally learned Bayesian networks, based on the fast greedy equivalent search algorithm. The method is competitive with the state of the art in terms of the Matthews correlation coefficient, which takes into account both precision and recall, while also improving upon it in terms of speed, scaling up to tens of thousands of variables and being able to use empirical knowledge about the topological structure of gene regulatory networks. To showcase the ability of our method to scale to massive networks, we apply it to learning the gene regulatory network for the full human genome using data from samples of different brain structures (from the Allen Human Brain Atlas). Furthermore, this Bayesian network model should predict interactions between genes in a way that is clear to experts, following the current trends in explainable artificial intelligence. To achieve this, we also present a new open-access visualization tool that facilitates the exploration of massive networks and can aid in finding nodes of interest for experimental tests.

Vital information is only worth one thumbnail: Towards efficient human pose estimation

In pursuit of impressive performance, existing DCNN-based approaches of human pose estimation usually use massive networks and large-size images to train a deep model. When applying these deep based methods in real-time systems, current works try to compress the deep network by reducing the number of layers and channels, but such approaches are complex and poorly generalized since they require elaborate design of small-scale network structures. Based on the fact that large-size images contain redundant information, in this paper, we explore the influence of image-size on system complexity and propose a novel framework called ThumbPose to accelerate and compress deep models by inferring on thumbnail representations in the task of human pose estimation. In our framework, we first propose a style supervised online downscaler to reduce an input image into a thumbnail image. Furthermore, a training strategy of dual-branch auto-encoding is designed to obtain effective and accurate thumbnail representation in a knowledge distillation manner, which is further used to maintain the performance of thumbnail images as the original-size input images. For heat-map based human pose estimation, ThumbPose is an orthogonal and implementation-friendly method, that can not only compress and accelerate the inference network but also obtain an image downscaler in a supervised manner that can be used in other high-level tasks (e.g. detection, segmentation, etc. in practical applications). Extensive experiments on MS COCO dataset demonstrate the effectiveness of our proposed method, and ThumbPose achieves superior performance (＋ 1.3% AP and ＋ 0.7% AR) with negligible additional cost (<0.2 GFLOPs) compared to previous state-of-the-art methods when using small-size images as inputs. Moreover, experiments on MPII show that our model achieves higher accuracy (＋ 0.2% Mean@0.5) with minimal computation (2.5 GFLOPs) compared to superior lightweight models obtained by the network compression methods.

Representing and Inferring Massive Network Traffic Condition: A Case Study in Nashville, Tennessee

Intelligent transportation systems (ITSs) usually require monitoring of massive road networks and gathering traffic data at a high spatial and temporal resolution. This leads to the accumulation of substantial data volumes, necessitating the development of more concise data representations. Approaches like principal component analysis (PCA), which operate within subspaces, can construct precise low-dimensional models. However, interpreting these models can be challenging, primarily because the principal components often encompass a multitude of links within the traffic network. To overcome this issue, this study presents a novel approach for representing and indexing network traffic conditions through weighted CUR matrix decomposition integrated with clustering analysis. The proposed approach selects a subset group of detectors from the original network to represent and index traffic condition through a matrix decomposition method, allowing for more efficient management and analysis. The proposed method is evaluated using traffic detector data from the city of Nashville, TN. The results demonstrate that the approach is effective in representing and indexing network traffic conditions, with high accuracy and efficiency. Overall, this study contributes to the field of network traffic monitoring by proposing a novel approach for representing massive traffic networks and exploring the effects of incorporating clustering into CUR decomposition. The proposed approach can help traffic analysts and practitioners to more efficiently manage and analyze traffic conditions, ultimately leading to more effective transportation systems.

Robotic sensing for buried pipes with sound waves

The length of buried sewer and drainage network in Europe is several million kilometres. Autonomous robots are being developed to inspect this massive network of pipes pervasively. These inspection technologies traditionally rely on CCTV images. However, detection of the condition of buried pipes with autonomous robots is challenging computationally. Acoustic waves provide an efficient alternative to conventional CCTV methods to detect a range of artefacts that can lead to pipe failure and map these conditions. This paper presents an acoustic method for simultaneous condition detection, localization, and classification in air-filled pipes. A microphone array is used to estimate the reflection coefficient from a range of artefacts. This information is used together with a regularization method. A wavelet basis function is adapted to enhance the fidelity of collected acoustic data. It is shown that the wavelet components can also be used to train and to test a support vector machine (SVM) classifier for the condition identification. This work can also inform the route planning and low-level control algorithms for autonomous robots which are being developed for the inspection of buried pipes.

DomainNet: Homograph Detection and Understanding in Data Lake Disambiguation

Modern data lakes are heterogeneous in the vocabulary that is used to describe data. We study a problem of disambiguation in data lakes: How can we determine if a data value occurring more than once in the lake has different meanings and is therefore a homograph? While word and entity disambiguation have been well studied in computational linguistics, data management, and data science, we show that data lakes provide a new opportunity for disambiguation of data values, because tables implicitly define a massive network of interconnected values. We introduce DomainNet , which efficiently represents this network, and investigate to what extent it can be used to disambiguate values without requiring any supervision. DomainNet leverages network-centrality measures on a bipartite graph whose nodes represent data values and attributes to determine if a value is a homograph. A thorough experimental evaluation demonstrates that state-of-the-art techniques in domain discovery cannot be re-purposed to compete with our method. Specifically, using a domain discovery method to identify homographs achieves an F1-score of 0.38 versus 0.69 for DomainNet , which separates homographs well from data values that have a unique meaning. On a real data lake, our top-100 precision is 93%. Given a homograph, we also present a novel method for determining the number of meanings of the homograph and for assigning its data lake attributes to a meaning. We show the influence of homographs on two downstream tasks: entity-matching and domain discovery.

On the Synchronous Ethernet for a Massive Networking Deployment: Insight Into a Tailored Cosimulated Testbed

Digital communications have a minimum synchronization requirement: the end user of a telecommunication system has to lock into the right bit rhythm sent by the other connection partner. Nevertheless, synchronization in the telecommunication context turns out to be broader than two connection partners locally linked: the suitable feed of a standard time, within many telecommunication domains, has vital importance for many applications to properly handle the demanded network functionalities. The time feed in multidomain scenarios makes a time path, which becomes a nested built-in network. Generally, the data distribution follows the time path in many telecommunication systems. However, the data path may not follow the time path for all scenarios and could partially follow some network branches, usually at the network border. To ensure efficient and controllable synchronization, we focus on the study of time paths. This article provides a first insight into a tailored cosimulated testbed, implemented to determine the time path behavior in terms of jitter and to supervise the drift from the primary reference clock (PRC) with more than 20 cascaded nodes, the maximum achievable cascaded depth within the current G.8262 standard. This cascading must meet the requirements of the International Telecommunication Union (ITU-T) standards G.8262/G.8261 in terms of long-term jitter (wander) and short-term jitter (jitter) to ensure a tolerable drift compared with the central clock. In particular, for Synchronous Ethernet (SyncE), the standard does not provide possible limits for the jitter beyond 20 synchronized nodes. The numerical results, with the extended number of nodes, show that this scenario remains feasible, the parameters being below the masks proposed by the standards.

Efficient Network Slicing for 5G Services in Cloud Fog-RAN Deployment Over WDM Network

Network slicing in fifth generation (5G) radio access network (RAN) enables serving massive network traffic with diverse and stringent quality of service (QoS) requirements. Multiple logical networks can be built using RAN slicing over a single RAN infrastructure. This paper considers three different types of slices that are standardized by third generation partner project (3GPP): ultra-reliable low-latency communication (URLLC), enhanced mobile broadband (eMBB), and massive machine type communication (mMTC). Each slice type has unique requirements for data rate, latency, and reliability. Cloud RAN (C-RAN) was proposed to address the requirements of 5G services, which involves physical separation between the remote radio head (RRH) and baseband unit (BBU) in 2-layers. While C-RAN enables more efficient resource utilization and energy consumption, it limits network scalability. Furthermore, C-RAN is unable to meet the stringent latency demands of URLLC services, as well as the massive fronthaul capacity required for eMBB requests. To address this issue, we propose a novel cloud fog RAN (CF-RAN) over wavelength division multiplexing (WDM) architecture. In CF-RAN over WDM the RAN functions are divided into 3 layers, which include the RRH at layer 1, fog nodes at layer 2, and BBU hotels at layer 3. We employ the emerging fog computing paradigm in optical and wireless networks in this suggested architecture. To facilitate low latency URLLC requests, the fog nodes are located closer to the cell site (CS). We propose an integer linear programming (ILP)-based mathematical model. The model's objective is to decrease the number of active BBU hotels and fog nodes while remaining compliant with practical network restrictions. Furthermore, a low complexity greedy heuristic algorithm is proposed to solve the problem and is compared to the branch & bound (B&B) algorithm, which is assumed to provide an optimal solution with exponential complexity. The proposed 3-layer CF-RAN over WDM architecture achieves a 70% improvement in BBU centralization and a 50% reduction in request blocking when compared to the standard 2-layer architecture.

A multimodal hybrid parallel network intrusion detection model

With the rapid growth of Internet data traffic, the means of malicious attack become more diversified. The single modal intrusion detection model cannot fully exploit the rich feature information in the massive network traffic data, resulting in unsatisfactory detection results. To address this issue, this paper proposes a multimodal hybrid parallel network intrusion detection model (MHPN). The proposed model extracts network traffic features from two modalities: the statistical information of network traffic and the original load of traffic, and constructs appropriate neural network models for each modal information. Firstly, a two-branch convolutional neural network is combined with Long Short-Term Memory (LSTM) network to extract the spatio-temporal feature information of network traffic from the original load mode of traffic, and a convolutional neural network is used to extract the feature information of traffic statistics. Then, the feature information extracted from the two modalities is fused and fed to the CosMargin classifier for network traffic classification. The experimental results on the ISCX-IDS 2012 and CIC-IDS-2017 datasets show that the MHPN model outperforms the single-modal models and achieves an average accuracy of 99.98 % . The model also demonstrates strong robustness and a positive sample recognition rate.