Dynamic Dataflow Research Articles

HAIS-IDS:A Hybrid Artificial Immune System Model for Intrusion Detection in IoT

The application of the Internet of Things(IoT) is increasing exponentially, the dynamic data flow and distributive operation over low resource devices possesses huge threat to sensitive human data. This paper introduces an artificial immune system (AIS) based approach to intrusion detection in IoT network ecosystems, the proposed approach implements dual-layered AIS; which is robust to zero-day attacks and designed to adapt new types of attack classes in the form of antibodies.In this paper, a Hybrid method has been presented which uses Hybrid of Clonal Selection using Variation auto-encoders as Innate Immune Layer and Apaptive Dentritic Model for identifying intrusions over IoT Specific Datasets.Moreover we present extensive empirical analysis over six IoT network benchmark datasets for semi-supervised multi-class classification task and obtain superior performance compared to five state-of-the-art baselines. Finally, VC-ADIS achieves 99.83% accuracy over MQTT-set dataset.

SparGD: A Sparse GEMM Accelerator with Dynamic Dataflow

Deep learning has become a highly popular research field, and previously deep learning algorithms ran primarily on CPUs and GPUs. However, with the rapid development of deep learning, it was discovered that existing processors could not meet the specific large-scale computing requirements of deep learning, and custom deep learning accelerators have become popular. The majority of the primary workloads in deep learning are general matrix-matrix multiplications (GEMMs), and emerging GEMMs are highly sparse and irregular. The TPU and SIGMA are typical GEMM accelerators in recent years, but the TPU does not support sparsity, and both the TPU and SIGMA have insufficient utilization rates of the Processing Element (PE). We design and implement SparGD, a sparse GEMM accelerator with dynamic dataflow. SparGD has specific PE structures, flexible distribution networks and reduction networks, and a simple dataflow switching module. When running sparse and irregular GEMMs, SparGD can maintain high PE utilization while utilizing sparsity, and can switch to the optimal dataflow according to the computing environment. For sparse, irregular GEMMs, our experimental results show that SparGD outperforms systolic arrays by 30 times and SIGMA by 3.6 times.

An autocorrelation incremental fuzzy clustering framework based on dynamic conditional scoring model

This paper focuses on the real-time dynamic clustering analysis of power load data based on the dynamic conditional score (DCS) model, and an autocorrelation increment fuzzy C-means clustering algorithm based on the DCS model is proposed. (1) The paper addresses the problem that current power load clustering methods, when performing time series data mining, tend to focus on capturing the mean structure while ignoring the variance characteristics of the data, making it difficult to effectively capture the structural information of time series data. The DCS model is used as the statistical model basis for clustering analysis, and the time series is clustered based on the estimated conditional moment characteristics of the model, dynamically capturing data features such as the mean, variance, and sequence correlation of time series data, effectively improving the clustering performance. (2) This paper also addresses the issue that current power load clustering methods tend to focus on static datasets of user power loads and cannot effectively handle the data stream clustering problem with time series characteristics in practical applications. The DCS model parameter dataset and the autocorrelation increment fuzzy clustering algorithm are used to conduct a dynamic data flow analysis of user electricity behaviour evolution and pattern continuous updating research for power loads. The clustering results are dynamically updated based on the user's power load data stream using the proposed algorithm, achieving research on a universal clustering model and secure and efficient algorithms in a big data environment. (3) The paper verifies the clustering performance of the proposed method using power load time series data provided by a Chinese power supply company as a case dataset. The clustering evaluation index shows that the proposed algorithm has high clustering accuracy and good clustering performance. Additionally, different power supply recommendations are proposed for different customer electricity types in the obtained clustering results to provide more personalized power services.

Abnormal Traffic Detection Method of Internet of Things Based on Deep Learning in Edge Computing Environment

In this paper, a method based on deep learning to detect abnormal traffic of IoTs in edge computing environment is proposed. Firstly, the data are preprocessed by data cleaning, normalization, oversampling and undersampling, and data set segmentation to obtain a data set with balanced data distribution. Secondly, a method of calculating feature information based on data increment is adopted, which can accurately extract feature information from the dynamic data flow. Finally, the convolution neural network (CNN) is used to extract the local features of the data, and the bi-directional gated loop unit (BiGRU) is used to extract the long sequence correlation of the data. The two networks work together to extract data features. The self-focus mechanism is introduced to deal with redundant data. Experiments show that the accuracy, recall and [Formula: see text]1 value of the proposed method are 97.36%, 98.38% and 97.16%, respectively, in the normal class, which are higher than the comparison algorithm.

Energy Minimization of Dynamic Multi-UAV Communication Network for Cooperative MultiHop Data Gathering

This study proposes a minimum-energy operational planning problem for multiple unmanned aerial vehicles (UAVs) conducting a cooperative multi-hop data-gathering mission. A multi-UAV ad-hoc network collects data from multiple sources and transmits them to a ground base station. The proposed mixed-integer nonlinear programming (MINLP) formulation simultaneously determines cooperative task allocation, data gathering schedule, dynamic aerial data flow, and UAV trajectories to minimize operational energy consumption. A hierarchical two-phase solution procedure that decomposes the original problem into a series of less complex problems and solves them efficiently is developed. The effectiveness of the proposed formulation and the solution procedure is demonstrated through numerical experiments and comparison with benchmarking operational schemes.

FlexMoE: Scaling Large-scale Sparse Pre-trained Model Training via Dynamic Device Placement

With the increasing data volume, there is a trend of using large-scale pre-trained models to store the knowledge into an enormous number of model parameters. The training of these models is composed of lots of dense algebras, requiring a huge amount of hardware resources. Recently, sparsely-gated Mixture-of-Experts (MoEs) are becoming more popular and have demonstrated impressive pretraining scalability in various downstream tasks. However, such a sparse conditional computation may not be effective as expected in practical systems due to the routing imbalance and fluctuation problems. Generally, MoEs are becoming a new data analytics paradigm in the data life cycle and suffering from unique challenges at scales, complexities, and granularities never before possible. In this paper, we propose a novel DNN training framework, FlexMoE, which systematically and transparently address the inefficiency caused by dynamic dataflow. We first present an empirical analysis on the problems and opportunities of training MoE models, which motivates us to overcome the routing imbalance and fluctuation problems by a dynamic expert management and device placement mechanism. Then we introduce a novel scheduling module over the existing DNN runtime to monitor the data flow, make the scheduling plans, and dynamically adjust the model-to-hardware mapping guided by the real-time data traffic. A simple but efficient heuristic algorithm is exploited to dynamically optimize the device placement during training. We have conducted experiments on both NLP models (e.g., BERT and GPT) and vision models (e.g., Swin). And results show FlexMoE can achieve superior performance compared with existing systems on real-world workloads --- FlexMoE outperforms DeepSpeed by 1.70x on average and up to 2.10x, and outperforms FasterMoE by 1.30x on average and up to 1.45x.

Run-Time Remapping Algorithm of Dataflow Actors on NoC-Based Heterogeneous MPSoCs

Multiprocessor system-on-chip (MPSoC) platforms have been emerging as the main solution to cope with processor frequency ceiling and power density issues while still improving performances. Then, network-on-chip (NoC) has been adopted to provide the increasing number of processors with the required communication bandwidth as well as with the necessary flexibility. Video processing and streaming applications are adopting dynamic dataflow model of computation as the need for high performance parallel computing is growing. Dataflow applications executed on modern MPSoC-based architectures are becoming increasingly dynamic and more data-dependent. Different tasks execute concurrently with significant modifications in their workloads and resource demanding over time depending on the input data. Hence, adopting any static or offline dynamic scheduling for mapping tasks will not cope with the computation variations. This article introduces an original run-time mapping algorithm based on the Move Based (MB) method targeting a dedicated heterogeneous NoC-based MPSoC architecture to achieve workload balancing and optimized communication traffic. The performance of the proposed algorithm is verified by conducting cycle-accurate SystemC simulations of the adopted NoC implementing a real MPEG4-SP decoder. The obtained results reveal the effectiveness of our proposed algorithm. For various real-life videos, the proposed algorithm systematically succeeded to enhance significantly the performance.

Development of a fully automated platform for agar-based measurement of viable bacterial growth.

Dynamic in vitro antibacterial studies provide valuable insight on effective dosing strategies prior to translating to in vivo models. Frequent sampling is required to monitor the pharmacodynamics (PD) of these studies, leading to significant work when quantifying the bacterial load of the samples. Spreading a bacterial suspension on agar to allow colony counting is a proven process for measuring very low levels of growth, but commercial automation equipment to handle agar plating and colony counting at scale is not readily available. We describe a process to greatly decrease the hands-on time required for PD assays by utilizing general-purpose liquid handling robots to plate bacteria and a custom-made plate imager to automate colony counting. The platform developed handles the biological assay from beginning to end as well as sample tracking at each step of the process. The process relies heavily on custom automation scheduling software to enable dynamic process decisions and coordinate data flow throughout. Using the described platform, we can efficiently quantify >100 PD samples per day while maintaining the necessary dynamic range of the assay. Alleviating the main bottleneck in the dynamic antibacterial studies has allowed us to accelerate the rate of experiments to provide antibacterial dosing data within shorter timelines.

Blockchain-Empowered Service Management for the Decentralized Metaverse of Things

The future of networking will be driven by the current emerging trends of combining the physical and virtual realities in cyberspace. Considering the ambient pandemic challenges, the role of virtual and augmented reality will definitely grow over time by transforming into the paradigm of the Metaverse of Things, where each person, thing or other entity will simultaneously exist within multiple synchronized realities. In this paper, we propose a novel framework for future metaverse applications composed of multiple synchronized data flows from multiple operators through multiple wearable devices and with different quality requirements. A new service quality model is proposed based on a customizable utility function for each individual data flow. The proposed approach is based on dynamic fine-grained data flow allocation and service selection using non-fungible tokens, which can be traded over the blockchain among users and operators in a decentralized mobile network environment.

On-line Recognition of Abnormal Patterns in Bivariate Autocorrelated Process Using Random Forest

It is not uncommon that two or more related process quality characteristics are needed to be monitored simultaneously in production process for most of time. Meanwhile, the observations obtained online are often serially autocorrelated due to high sampling frequency and process dynamics. This goes against the statistical I.I.D assumption in using the multivariate control charts, which may lead to the performance of multivariate control charts collapse soon. Meanwhile, the process control method based on pattern recognition as a non-statistical approach is not confined by this limitation, and further provide more useful information for quality practitioners to locate the assignable causes led to process abnormalities. This study proposed a pattern recognition model using Random Forest (RF) as pattern model to detect and identify the abnormalities in bivariate autocorrelated process. The simulation experiment results demonstrate that the model is superior on recognition accuracy (RA) (97.96%) to back propagation neural networks (BPNN) (95.69%), probability neural networks (PNN) (94.31%), and support vector machine (SVM) (97.16%). When experimenting with simulated dynamic process data flow, the model also achieved better average running length (ARL) and standard deviation of ARL (SRL) than those of the four comparative approaches in most cases of mean shift magnitude. Therefore, we get the conclusion that the RF model is a promising approach for detecting abnormalities in the bivariate autocorrelated process. Although bivariate autocorrelated process is focused in this study, the proposed model can be extended to multivariate autocorrelated process control.

Design of effective value calculation model for dynamic dataflow of infrared gas online monitoring.

The development of "CC30A CH4-CO2 combined analyzer" with infrared gas sensor as the core detection device can be widely used in online gas component analysis. In data analysis, the maximum value and arithmetic mean of the sensor data for each test period are not effective value. The characteristics of the dynamic data are: (1) Each DAW completes one test for one parameter, there is a unique effective value; (2) In test state, the fluctuation of the sensor value gradually decreases when approaching to the end of the test. An effective value calculation model was designed using the method of dimensionality reduction of dynamic data. The model was based on the distribution characteristics of the process data, and consists of 4 key steps: (1) Identify the Data Analysis Window (DAW) and build DAW dataset; (2) Calculate the value of optimal DAW dataset segmentation and build DAW subdataset; (3) Calculate the arithmetic mean (Mc) and count the amount of data in each subdataset (Fc), and build the optimal segmentation statistical set; (4) Effective value calculation and error evaluation. Calculation result with 50 sets of monitor data conformed that the EVC model for dynamic data of gas online monitoring meets the requirements of experimental accuracy requirements and test error. This method can be independently calculated without relying on the feedback information of the monitoring device, and it has positive significance for using the algorithm to reduce the hardware design complexity.

Scheduling Data Flow between Data Centers Based on Software Defined Network

For intelligent control of network traffic, to solve the problem of low utilization of public network bandwidth, we put forward scheduling data flow between data center based on SDN technology. First, we connect the data center distributed in different locations by wide area network and exchange or share the research data of high performance. Then, the system can sense the utilization and performance of the network bandwidth resources between the data center. Based on the results of perception, we can dynamically adjust and optimize the path of data and maximize the utilization of network link. SDN is a new software based network structure. This paper uses SDN network architecture to schedule the traffic of data center, and constructs a two-layer network suitable for cloud computing and virtualization environment. It realizes the global, dynamic and intelligent data flow.

Research and Application of Fault Diagnosis Method for Automobile Electronic Control Engine Based on Data Stream Analysis

In the process of diagnosing automobile electronic control engine faults, using data flow analysis methods as the main fault diagnosis work can not only improve the efficiency of fault diagnosis, but also have a positive significance for the development of China’s automobile industry. The engine is not only the main component of the automobile, but also the key content that must be paid attention to in the development of the automobile industry. Once a car engine fails, it will have a great impact on the operation of the whole car. In order to be able to accurately grasp the specific fault conditions of automobile electronically controlled engines, we need to use effective fault diagnosis methods for analysis. At present, the application of dynamic data flow and static data flow analysis methods can accurately grasp the actual situation of the engine to a large extent. The use of data flow analysis to carry out effective troubleshooting and handling of the cause of the fault can reduce the possibility of engine failure. Experts need to analyze the specific conditions of the data flow during the research process, and discuss the specific application of the data flow analysis method in the process of automobile electronic control engine fault diagnosis. Thereby it can provide accurate reference for the fault diagnosis of automobile electronic control engine, ensure the safe operation of automobile electronic control engine, and improve the production efficiency of automobile enterprises.

Dynamic Dataflow Scheduling and Computation Mapping Techniques for Efficient Depthwise Separable Convolution Acceleration

Depthwise separable convolution (DSC) has become one of the essential structures for lightweight convolutional neural networks. Nevertheless, its hardware architecture has not received much attention. Several previous hardware designs incur either high off-chip memory traffic or large on-chip memory usage, and hence have deficiency in terms of hardware efficiency as well as performance. This paper proposes two efficient dynamic design techniques, i.e. adaptive row-based dataflow scheduling and adaptive computation mapping, to achieve a much better trade-off between hardware efficiency and performance for DSC-based lightweight CNN accelerator. The effectiveness and efficiency of the proposed dynamic design techniques have been extensively evaluated using six DSC-based lightweight CNNs. Compared with the reference architectures, the simulation results show the proposed architectural techniques can at least reduce on-chip buffer size by 50.4% and improve the performance of convolution calculation by 1.18× while maintaining the minimum off-chip memory traffic. MobileNetV2 is implemented on Zynq UltraScale+ ZCU102 SoC FPGA, and the results show the proposed accelerator can achieve 381.7 frames per second (fps), which is 1.43× of the reference design, and it can save about 36.3% on-chip buffer size compared with the reference design, while maintaining the same off-chip memory traffic.

Multi-paradigm modelling for cyber\u2013physical systems: a descriptive framework

The complexity of cyber–physical systems (CPSs) is commonly addressed through complex workflows, involving models in a plethora of different formalisms, each with their own methods, techniques, and tools. Some workflow patterns, combined with particular types of formalisms and operations on models in these formalisms, are used successfully in engineering practice. To identify and reuse them, we refer to these combinations of workflow and formalism patterns as modelling paradigms. This paper proposes a unifying (Descriptive) Framework to describe these paradigms, as well as their combinations. This work is set in the context of Multi-Paradigm Modelling (MPM), which is based on the principle to model every part and aspect of a system explicitly, at the most appropriate level(s) of abstraction, using the most appropriate modelling formalism(s) and workflows. The purpose of the Descriptive Framework presented in this paper is to serve as a basis to reason about these formalisms, workflows, and their combinations. One crucial part of the framework is the ability to capture the structural essence of a paradigm through the concept of a paradigmatic structure. This is illustrated informally by means of two example paradigms commonly used in CPS: Discrete Event Dynamic Systems and Synchronous Data Flow. The presented framework also identifies the need to establish whether a paradigm candidate follows, or qualifies as, a (given) paradigm. To illustrate the ability of the framework to support combining paradigms, the paper shows examples of both workflow and formalism combinations. The presented framework is intended as a basis for characterisation and classification of paradigms, as a starting point for a rigorous formalisation of the framework (allowing formal analyses), and as a foundation for MPM tool development.

Gamma — General Abstract Model for Multiset mAnipulation and dynamic dataflow model: An equivalence study

AbstractWith the increase of the search for computational models where the expression of parallelism occurs naturally, some paradigms arise as options for the current generation of computers. In this context, dynamic dataflow and Gamma—General Abstract Model for Multiset mAnipulation—emerge as interesting computational model choices. In dynamic dataflow model, operations are performed as soon as their associated operands are available, without rely on a Program Counter to dictate the execution order of instructions. The Gamma paradigm is based on a parallel multiset rewriting scheme. It provides a nondeterministic execution model inspired by an abstract chemical machinemetaphor, where operations are formulated as reactions that occur freely among matching elements belonging to the multiset. In this work, equivalence relations between the dynamic dataflow and Gamma paradigms are exposed and explored, while methods to convert from dataflow to Gamma paradigm and vice versa are provided. It is shown that vertices and edges of a dynamic dataflow graph can correspond, respectively, to reactions and multiset elements in the Gamma paradigm. This work provides the scientific community with the possibility of taking profit of both parallel programming models, contributing with a versatility component to researchers and developers.

Concurrency Analysis in Dynamic Dataflow Graphs

Dynamic dataflow scheduling enables effective exploitation of concurrency while making parallel programming easier. To this end, analyzing the inherent degree of concurrency available in dataflow graphs is an important task, since it may aid compilers or programmers to assess the potential performance a program can achieve via parallel execution. However, traditional concurrency analysis techniques only work for DAGs (directed acyclic graphs), hence the need for new techniques that contemplate graphs with cycles. In this paper we present techniques to perform concurrency analysis on generic dynamic dataflow graphs, even in the presence of cycles. In a dataflow graph, nodes represent instructions and edges describe dependencies. The novelty of our approach is that we allow concurrency between different iterations of the loops. Consequently, a set of concurrent nodes may contain instructions from different loops that can be proven independent. In this work, we provide a set of theoretical tools for obtaining bounds and illustrate implementation of parallel dataflow runtime on a set of representative graphs for important classes of benchmarks to compare measured performance against derived bounds.

Methodologies for Synthesizing and Analyzing Dynamic Dataflow Programs in Heterogeneous Systems for Edge Computing

Methodologies for Synthesizing and Analyzing Dynamic Dataflow Programs in Heterogeneous Systems for Edge Computing

The security of vulnerable senior citizens through dynamically sensed signal acquisition

AbstractTraditional signal recognition methods generally use biosensors for signal acquisition. With senior citizens, sensor signal acquisition will be affected by their movements. These signal fluctuations are large, and if the signal area cannot be fixed, it may result in problems such as data loss. The most important issue caused by data loss is the safety for vulnerable seniors. Therefore, here we study abnormal behavior recognition based on dynamic sensing. In this paper, we look to improve the problems that exist in traditional methods. Using the SW‐520D sensor, activity signals of the elderly are first collected. By comparing the received signal strength sets, dynamic sensor data flow of the abnormal behavior for senior citizens can be determined. A multiple linear regression estimation method is used to solve the problem of data loss in dynamic sensor data flow environments. We obtain system parameter thresholds in both area isolation and segmentation using the stochastic resonance method. From this, a direct notch is constructed that enters the dynamic sensor data stream, and the interference component filtering of abnormal behavior signals is processed. The amplitude‐frequency response feature extraction method is used for high‐precision isolation and segmentation of abnormal behavior signal areas such as falls, improving the accuracy of senior behavior signal recognition, and realizing safety monitoring for the elderly. The improved method was used to identify the signals of abnormal behaviors of young people. The minimum recognition error rate was only 2%, the recognition accuracy rate was as high as 98%, and the calculation time was only 19 ms.

Dynamic imbalanced business credit evaluation based on Learn++ with sliding time window and weight sampling and FCM with multiple kernels

A good model of business credit evaluation is an important tool for risk management. Although the dynamic imbalanced data flow is more consistent with the form of collected financial data in the actual situation, existing studies seldom research financial data as this form. This paper proposes a new ensemble model for dynamic imbalanced business credit evaluation based on the improved Learn++ and fuzzy c-means (FCM). To handle dynamic imbalanced financial data, Learn++ is improved by using a sliding time window (STW) and weight sampling (WS). This method is termed Learn++.STW-WS. STW can divide data with the same concept into the same dataset to solve the problem of concept drift which characteristic in dynamic data. Additionally, WS can redistribute the weights for samples of different classes to resolve the issue of imbalance. To satisfy the demand of Learn++.STW-WS on the prediction accuracy of a base classifier, FCM is improved by multiple kernels (MK), and is designated as MK-FCM. Several kernel functions are integrated to construct MK by the mean method, and MK is adopted to improve the calculation method of distances among points for FCM. Therefore, this new ensemble model can solve the problems of dynamic data and imbalanced classes at the same time. In the empirical research, financial data from Chinese listed companies are selected to evaluate business credit risk, and the associated models are adopted to make comparative analysis. The experiment results can fully demonstrate the good performance of the new ensemble model in terms of handling dynamic imbalanced financial data.