A self adaptive differential harmony search based optimized extreme learning machine for financial time series prediction

Dash, Rajashree; Dash, P.K.; Bisoi, Ranjeeta

doi:10.1016/j.swevo.2014.07.003

Cited by 84 publications

(26 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DE has demonstrated its robustness and power in a variety of applications, such as neural network learning [26]. DE has been now widely applied to solve various optimization problems from various fields, such as predicting blast-induced ground vibrations [28], optimization of air quantity regulation in mine ventilation networks [29], time series prediction [30], and power systems optimization [31].…”

Section: Differential Evaluationmentioning

confidence: 99%

Prediction of blast-induced flyrock using differential evolution algorithm

Dehghani

Shafaghi

2016

Engineering with Computers

View full text Add to dashboard Cite

loading and hauling. Fragments can be thrown beyond the desired pile limit, which is normal but is considered adverse effect of blasting and is called flyrock. Fragments propelled far beyond predefined safety limit are considered security breach and are called wild flyrock [1].Due to high potential to cause damage to machinery and nearby structures and to cause injuries, even fatal, to personnel, flyrock is the most dangerous adverse effect of blasting and this phenomenon is responsible for 28.3 % of the damages and injuries in surface mining activities [2].To prevent flyrock problem, various parameters such as the physico-mechanical properties of rock mass, explosives specifications and geometrical aspects of the blasting pattern should be considered while designing a blasting pattern. For example, flyrock may occur in situations where there is insufficient stemming, too small a burden because of overbreak from the preceding or proceeding blast, planes of weaknesses in rock which reduce resistance to blasting, and finally existence of loose rock fragment on top of the bench [3]. Explosives with high energy can increase the probability of the flyrock. Most of the conventional formula used the TNT strength instead of the explosive strength.To convert this factor, usually, the ballistic mortar test was used (Fig. 1).Since this phenomenon is very dangerous, many researchers trying to establish the flyrock prediction models. Lundborg presented an equation for estimating the flyrock based on the hole diameter and specific charge as follows [4]:where L is the maximum rock projection (m), D is the hole diameter (in) and q is the specific charge (kg/m 3 ). Also, Lundborg et al. established another empirical model based on hole diameter as follows [5]:Abstract Flyrock is an undesirable phenomenon in blasting operations. Due to high potential to cause damage to machinery and nearby structures and to cause injuries, even fatal, to personnel, flyrock is the most dangerous adverse effect of blasting. For controlling and decreasing the effect of this phenomenon, it is necessary to predict it. Because of multiplicity of effective parameters and complexity of interactions among these parameters, empirical methods may not be fully appropriate for flyrock estimation. The scope of this study is to predict flyrock induced by blasting through a novel approach based on the combination of differential evaluation algorithm (DE) and dimensional analysis algorithm (DA). For this purpose, the parameters of 300 blasting operations were accurately recorded and flyrock distances were measured for each operation. In the next stage, two new empirical predictors were developed to predict flyrock distance. The results clearly showed the superiority of the proposed DE-DA model in comparison with the empirical approaches.

show abstract

Section: Differential Evaluationmentioning

confidence: 99%

Prediction of blast-induced flyrock using differential evolution algorithm

Dehghani

Shafaghi

2016

Engineering with Computers

View full text Add to dashboard Cite

show abstract

“…Step IV -Performance Evaluation Closing Price: For measuring the performance of the model for predicting the closing the Mean Absolute Percentage Error (MAPE) and Root Mean Squared Error (RMSE) are used, which are defined in (16) and (17).…”

Section: -Use Of Technical Indicators For Smoothening Data Pointsmentioning

confidence: 99%

“…Two Indian stock market indices such as BSE Sensex and CNX Nifty are used as the experimental data. The proposed model has been compared with the recent models such as FLIT2FNS [5] and SADHS-OELM [16]. The objective of this paper is to get in-depth knowledge in the stock market in Indian scenario with the two above mentioned stock indices using technical analysis methods and tools and to predict 1 day, 1 week, and 1 month ahead trends, volatility and momentum of stock indices in advance.…”

Section: Introductionmentioning

confidence: 99%

A Naïve SVM-KNN based stock market trend reversal analysis for Indian benchmark indices

Nayak

Mishra

Rath

2015

Applied Soft Computing

140

View full text Add to dashboard Cite

“…Hosseinioun presented the use of wavelet transform and adaptive ELM to forecast outlier occurrence in stock market time series [18]. Dash presented an optimized ELM for predicting financial time series [19]. The ELM based prediction methods have high accuracy and fast learning speed in off-line cases, but they are not suitable for online applications.…”

Section: Introductionmentioning

confidence: 99%

Time Series Prediction Based on Adaptive Weight Online Sequential Extreme Learning Machine

Huang

Lü

2017

Applied Sciences

View full text Add to dashboard Cite

A novel adaptive weight online sequential extreme learning machine (AWOS-ELM) is proposed for predicting time series problems based on an online sequential extreme learning machine (OS-ELM) in this paper. In real-world online applications, the sequentially coming data chunk usually possesses varying confidence coefficients, and the data chunk with a low confidence coefficient tends to mislead the subsequent training process. The proposed AWOS-ELM can improve the training process by accessing the confidence coefficient adaptively and determining the training weight accordingly. Experiments on six time series prediction data sets have verified that the AWOS-ELM algorithm performs better in generalization performance, stability, and prediction ability than the OS-ELM algorithm. In addition, a real-world mechanical system identification problem is considered to test the feasibility and efficacy of the AWOS-ELM algorithm.

show abstract

A self adaptive differential harmony search based optimized extreme learning machine for financial time series prediction

Cited by 84 publications

References 33 publications

Prediction of blast-induced flyrock using differential evolution algorithm

Prediction of blast-induced flyrock using differential evolution algorithm

A Naïve SVM-KNN based stock market trend reversal analysis for Indian benchmark indices

Time Series Prediction Based on Adaptive Weight Online Sequential Extreme Learning Machine

Contact Info

Product

Resources

About