Cloud-Based Parameter-Driven Statistical Services and Resource Allocation in a Heterogeneous Platform on Enterprise Environment

Lee, Sung-Ju; Jeong, Taikyeong

doi:10.3390/sym8100103

Cited by 7 publications

(7 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 2 shows that a comparison of the recent yearly data by layer x = 0, which includes real data, 20%, 13%, 8%, and 6 %, respectively. Each colored line shows five layer-by-layer predictions, and the legend on the left shows the stock price index of the S&P 500 [27,28] in Figure 3. It can be seen that the main inflection point and the amount of network applied are very similar to the real data, that is, the actual measured data.…”

Section: Analysis and Resultsmentioning

confidence: 99%

Forecasting Purpose Data Analysis and Methodology Comparison of Neural Model Perspective

Lee

Jeong

2017

Symmetry

Self Cite

View full text Add to dashboard Cite

Abstract:The goal of this paper is to compare and analyze the forecasting performance of two artificial neural network models (i.e., MLP (multi-layer perceptron) and DNN (deep neural network)), and to conduct an experimental investigation by data flow, not economic flow. In this paper, we investigate beyond the scope of simple predictions, and conduct research based on the merits and data of each model, so that we can predict and forecast the most efficient outcomes based on analytical methodology with fewer errors. In particular, we focus on identifying two models of neural networks (NN), a multi-layer perceptron (i.e., MLP) model and an excellent model between the neural network (i.e., DNN) model. At this time, predictability and accuracy were found to be superior in the DNN model, and in the MLP model, it was found to be highly correlated and accessible. The major purpose of this study is to analyze the performance of MLP and DNN through a practical approach based on an artificial neural network stock forecasting method. Although we do not limit S&P (i.e., Standard&Poor's 500 index) to escape other regional exits in order to see the proper flow of capital, we first measured S&P data for 100 months (i.e., 407 weeks) and found out the following facts: First, the traditional artificial neural network (ANN) model, according to the specificity of each model and depending on the depth of the layer, shows the model of the prediction well and is sensitive to the index data; Second, comparing the two models, the DNN model showed better accuracy in terms of data accessibility and prediction accuracy than MLP, and the error rate was also shown in the weekly and monthly data; Third, the difference in the prediction accuracy of each model is not statistically significant. However, these results are correlated with each other, and are considered robust because there are few error rates, thanks to the accessibility to various other prediction accuracy measurement methodologies.

show abstract

Section: Analysis and Resultsmentioning

confidence: 99%

Forecasting Purpose Data Analysis and Methodology Comparison of Neural Model Perspective

Lee

Jeong

2017

Symmetry

Self Cite

View full text Add to dashboard Cite

show abstract

“…To evaluate the performance of the fault-tolerant system, it was desired to have an evaluation kit 11,12 with the required hardware and software capabilities to handle the high data transfer rate and processing power along with software development tools and performance analyzers. 13,14 For instance, IBM PowerPC 750GX/GL evaluation board, having IBM PPC750GX processor 12 and Tundra TSI108 15,16 host bridge with supporting circuits and components as shown in Figure 2, was selected for the said purpose. The PPC750GX/GL is targeted for high-performance, low-power systems (2.5 W typical and 3.7 W maximum) that use a 60 3 bus.…”

Section: Proposed Systemmentioning

confidence: 99%

“…For instance, IBM PowerPC 750GX/GL evaluation board, having IBM PPC750GX processor 12 and Tundra TSI108 15,16 host bridge with supporting circuits and components as shown in Figure 2, was selected for the said purpose. The PPC750GX/GL is targeted for high-performance, low-power systems (2.5 W typical and 3.7 W maximum) that use a 60× bus.…”

Section: Proposed Systemmentioning

confidence: 99%

Highly scalable intelligent sensory application and time domain matrix for safety-critical system design

Jeong

2018

International Journal of Distributed Sensor Networks

View full text Add to dashboard Cite

The designs of highly scalable intelligent sensory application-Ethernet-based communication architectures-are moving toward the integration of a fault recovery and fault-detection algorithm on the automotive industry. In particular, each port on the same network interface card design is required to provide highly scalable and low-latency communication. In this article, we present a study of intelligent sensory application for the Ethernet-based communication architecture and performance of multi-port configuration which is mainly used in safety-enhanced application such as automotive, military, finance, and aerospace, in other words, safety-critical applications. Our contributions and observations on the highly scalable intelligent behavior: (1) proposed network interface card board design scheme and architecture with multi-port configuration are a stable network configuration; (2) timing matrix is defined for fault detection and recovery time; (3) experimental and related verification methods by cyclic redundancy check between client-server and testing platform provide comparable results to each port configurations; and (4) application program interface-level algorithm is defined to make network interface card ready for fault detection.

show abstract

“…Research on processing and analyzing big data in the IoT (Internet of Things) field has attracted considerable attention lately. In particular, parallel processing techniques, cloud computing technology, research for providing real-time services to users, and encryption have been actively investigated to find ways to more efficiently process large amounts of data [ 1 , 2 , 3 , 4 , 5 ]. Recently, an increase in the number of single-person households has led to studies on the behavior and control of companion animals, specifically the use of IoT sensor technology for the management of pet dogs.…”

Section: Introductionmentioning

confidence: 99%

Resource-Efficient Pet Dog Sound Events Classification Using LSTM-FCN Based on Time-Series Data

Kim

Chung

et al. 2018

Sensors

Self Cite

View full text Add to dashboard Cite

The use of IoT (Internet of Things) technology for the management of pet dogs left alone at home is increasing. This includes tasks such as automatic feeding, operation of play equipment, and location detection. Classification of the vocalizations of pet dogs using information from a sound sensor is an important method to analyze the behavior or emotions of dogs that are left alone. These sounds should be acquired by attaching the IoT sound sensor to the dog, and then classifying the sound events (e.g., barking, growling, howling, and whining). However, sound sensors tend to transmit large amounts of data and consume considerable amounts of power, which presents issues in the case of resource-constrained IoT sensor devices. In this paper, we propose a way to classify pet dog sound events and improve resource efficiency without significant degradation of accuracy. To achieve this, we only acquire the intensity data of sounds by using a relatively resource-efficient noise sensor. This presents issues as well, since it is difficult to achieve sufficient classification accuracy using only intensity data due to the loss of information from the sound events. To address this problem and avoid significant degradation of classification accuracy, we apply long short-term memory-fully convolutional network (LSTM-FCN), which is a deep learning method, to analyze time-series data, and exploit bicubic interpolation. Based on experimental results, the proposed method based on noise sensors (i.e., Shapelet and LSTM-FCN for time-series) was found to improve energy efficiency by 10 times without significant degradation of accuracy compared to typical methods based on sound sensors (i.e., mel-frequency cepstrum coefficient (MFCC), spectrogram, and mel-spectrum for feature extraction, and support vector machine (SVM) and k-nearest neighbor (K-NN) for classification).

show abstract

Cloud-Based Parameter-Driven Statistical Services and Resource Allocation in a Heterogeneous Platform on Enterprise Environment

Cited by 7 publications

References 23 publications

Forecasting Purpose Data Analysis and Methodology Comparison of Neural Model Perspective

Forecasting Purpose Data Analysis and Methodology Comparison of Neural Model Perspective

Highly scalable intelligent sensory application and time domain matrix for safety-critical system design

Resource-Efficient Pet Dog Sound Events Classification Using LSTM-FCN Based on Time-Series Data

Contact Info

Product

Resources

About