scholarly journals Machine-Learned Recognition of Network Traffic for Optimization through Protocol Selection

Computers ◽  
2021 ◽  
Vol 10 (6) ◽  
pp. 76
Author(s):  
Hamidreza Anvari ◽  
Paul Lu
Keyword(s):  
Time Series Data ◽  
Data Transfer ◽  
Network Protocols ◽  
Fine Tuning ◽  
Series Data ◽  
Trip Time ◽  
Background Traffic ◽  
Bulk Data ◽  
Protocol Selection ◽  
Selection Of

We introduce optimization through protocol selection (OPS) as a technique to improve bulk-data transfer on shared wide-area networks (WANs). Instead of just fine-tuning the parameters of a network protocol, our empirical results show that the selection of the protocol itself can result in up to four times higher throughput in some key cases. However, OPS for the foreground traffic (e.g., TCP CUBIC, TCP BBR, UDT) depends on knowledge about the network protocols used by the background traffic (i.e., other users). Therefore, we build and empirically evaluate several machine-learned (ML) classifiers, trained on local round-trip time (RTT) time-series data gathered using active probing, to recognize the mix of network protocols in the background with an accuracy of up to 0.96.

scholarly journals Curricular Concept Maps as Structured Learning Diaries: Collecting Data on Self-Regulated Learning and Conceptual Thinking for Learning Analytics Applications

2019 ◽  
Vol 6 (3) ◽  
Author(s):  
Ville Kivimäki ◽  
Joonas Pesonen ◽  
Jani Romanoff ◽  
Heikki Remes ◽  
Petri Ihantola
Keyword(s):  
Learning Analytics ◽  
Concept Maps ◽  
Time Series Data ◽  
Data Availability ◽  
Series Data ◽  
Structured Learning ◽  
Conceptual Thinking ◽  
Self Regulated Learning ◽  
Regulated Learning ◽  
Selection Of

The collection and selection of the data used in learning analytics applications deserve more attention. Optimally, selection of data should be guided by pedagogical purposes instead of data availability. Using design science research methodology, we designed an artifact to collect time-series data on students’ self-regulated learning and conceptual thinking. Our artifact combines curriculum data, concept mapping, and structured learning diaries. We evaluated the artifact in a case study, verifying that it provides relevant data, requires a limited amount of effort from students, and works in different educational contexts. Combined with learning analytics applications and interventions, our artifact provides possibilities to add value for students, teachers, and academic leaders.

Signal Processing of Microwave Imaging Brain Tumor Detection Using Superposition Windowing

2014 ◽  
Vol 654 ◽  
pp. 321-326 ◽  
Author(s):  
Kim Mey Chew ◽  
Rubita Sudirman ◽  
Norhudah Seman ◽  
Ching Yee Yong
Keyword(s):  
Signal Processing ◽  
Brain Tumor ◽  
Time Series Data ◽  
Tumor Detection ◽  
Microwave Imaging ◽  
Window Function ◽  
Series Data ◽  
Data Analyses ◽  
Window Functions ◽  
Selection Of

This paper discusses the selection of window function for signal processing in microwave imaging brain tumor detection. Most of the window functions are non-negative bell-shaped curves. This paper proposed a superposition windowing function for better time series data analyses and enhancement. The performance of the selected five window functions (Hamming, Blackman-Harris, Parzen, Chebyshev and Bartlett-Hanning) and the proposed superposition window were compared and evaluated. The results show the superposition window function is potentially reduce the unwanted noise and preserve important information of the signals.

Living on the Edge

2021 ◽  
Vol 2 (3) ◽  
pp. 1-31
Author(s):  
Thilina Buddhika ◽  
Matthew Malensek ◽  
Shrideep Pallickara ◽  
Sangmi Lee Pallickara
Keyword(s):  
Time Series ◽  
Data Streams ◽  
Time Series Data ◽  
Data Transfer ◽  
Holistic Approach ◽  
Series Data ◽  
Real World Data ◽  
Compact Representations ◽  
Performance Benchmarks ◽  
Effective Use

Voluminous time-series data streams produced in continuous sensing environments impose challenges pertaining to ingestion, storage, and analytics. In this study, we present a holistic approach based on data sketching to address these issues. We propose a hyper-sketching algorithm that combines discretization and frequency-based sketching to produce compact representations of the multi-feature, time-series data streams. We generate an ensemble of data sketches to make effective use of capabilities at the resource-constrained edge devices, the links over which data are transmitted, and the server pool where this data must be stored. The data sketches can be queried to construct datasets that are amenable to processing using popular analytical engines. We include several performance benchmarks using real-world data from different domains to profile the suitability of our design decisions. The proposed methodology can achieve up to ∼ 13 × and ∼ 2, 207 × reduction in data transfer and energy consumption at edge devices. We observe up to a ∼ 50% improvement in analytical job completion times in addition to the significant improvements in disk and network I/O.

scholarly journals A One-Stage Ensemble Framework based on Convolutional Autoencoder for Remaining Useful Life Estimation

2021 ◽  
Author(s):  
Yong-Keun Park ◽  
Min-Kyung Kim ◽  
Jumyung Um
Keyword(s):  
Neural Network ◽  
Time Series Data ◽  
Remaining Useful Life ◽  
Series Data ◽  
Proposed Model ◽  
Latent Space ◽  
Convolutional Autoencoder ◽  
Widespread Availability ◽  
Useful Life ◽  
Selection Of

Abstract The research on predictive maintenance of rotating machines, the most important element in manufacturing facilities, has been very active. The widespread availability of smart factory solutions has led to improved data collection from machines and processes and is able to provide key information. For our purpose, the collected information enables the maintenance system to predict the remaining useful life using deep learning models. The introduction of multi-layer perceptron of signal processing originating from bearings, in time series data, has been discussed in many publications. However, estimating accuracy for the remaining useful life is determined by the selection of the feature domain and the concatenation network model. Herein, we introduce a convolutional Autoencoder based on multi-domain ensemble learning in order to include various feature domains and a concatenation network operated by latent space into a single neural network. The performance of the proposed model is evaluated by using a simple health indicator and a PRONOSTIA dataset and compared with a simple concatenation model, 2-stage Autoencoder, and a recurrent neural network.

scholarly journals Metode ARIMA untuk Memodelkan Volume Produksi Kelapa Sawit pada PT. SOCFINDO di Kabupaten Aceh Tamiang

2021 ◽  
Vol 3 (2) ◽  
pp. 309-319
Author(s):  
Wiwin Apriani ◽  
◽  
Rahmi Hayati
Keyword(s):  
Mathematical Model ◽  
Time Series ◽  
Stationary State ◽  
Oil Palm ◽  
Time Series Data ◽  
Series Data ◽  
Test Results ◽  
Selection Of

This study aims to create a mathematical model that can be used to predict the amount of oil palm that will be produced at PT. Socfindo in Aceh Tamiang Regency in the coming period. The data used is data on the amount of oil palm that is ready to be produced every month in 2012-2015. The method used is the ARIMA method. The selection of this method is based on the data used, namely time series data. Before carrying out further testing, first, ensure that the data used meets the stationary state. From the test results, it is found that the data used fulfills the stationary state, then it is found that the MA (1) model can be used to predict the time series data. Furthermore, we obtain a model that can be used to predict the volume of oil palm production at PT. Socfindo is: Z_t = a_t-0.4096a_ (t-1) +521.57 With a_t ~ N (0; 29192.72)

Choosing the content of textual summaries of large time-series data sets

2006 ◽  
Vol 13 (1) ◽  
pp. 25-49 ◽  
Author(s):  
JIN YU ◽  
EHUD REITER ◽  
JIM HUNTER ◽  
CHRIS MELLISH
Keyword(s):  
Time Series ◽  
Gas Turbines ◽  
Time Series Data ◽  
Sensor Data ◽  
Series Data ◽  
Prototype System ◽  
Data Sets ◽  
Significant Patterns ◽  
Numeric Data ◽  
Selection Of

Natural Language Generation (NLG) can be used to generate textual summaries of numeric data sets. In this paper we develop an architecture for generating short (a few sentences) summaries of large (100KB or more) time-series data sets. The architecture integrates pattern recognition, pattern abstraction, selection of the most significant patterns, microplanning (especially aggregation), and realisation. We also describe and evaluate SumTime-Turbine, a prototype system which uses this architecture to generate textualsummaries of sensor data from gas turbines.

scholarly journals SELECTION OF INPUT VARIABLES OF NONLINEAR AUTOREGRESSIVE NEURAL NETWORK MODEL FOR TIME SERIES DATA FORECASTING

2020 ◽  
Vol 13 (2) ◽  
pp. 116-124
Author(s):  
Hermansah Hermansah ◽  
Dedi Rosadi ◽  
Abdurakhman Abdurakhman ◽  
Herni Utami
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Network Model ◽  
Neural Network Model ◽  
Time Series Data ◽  
Series Data ◽  
Input Variables ◽  
Nonlinear Autoregressive ◽  
Selection Of ◽  
Autoregressive Neural Network

NARNN is a type of ANN model consisting of a limited number of parameters and widely used for various applications. This study aims to determine the appropriate NARNN model, for the selection of input variables of nonlinear autoregressive neural network model for time series data forecasting, using the stepwise method. Furthermore, the study determines the optimal number of neurons in the hidden layer, using a trial and error method for some architecture. The NARNN model is combined in three parts, namely the learning method, the activation function, and the ensemble operator, to get the best single model. Its application in this study was conducted on real data, such as the interest rate of Bank Indonesia. The comparison results of MASE, RMSE, and MAPE values with ARIMA and Exponential Smoothing models shows that the NARNN is the best model used to effectively improve forecasting accuracy.

Sign in / Sign up

Export Citation Format

Share Document