Pub Date : 2012-06-24DOI: 10.1109/SHUSER.2012.6269014
S. A. Z. Abidin, M. Jaafar
This paper proposes a way to forecast the future closing price of small size companies in Bursa Malaysia by using geometric Brownian motion (GBM). Forecasting is restricted to short term investment because most of the investors aim to gain profit in short period of time. The reasons of choosing small size companies are because the asset prices are lower, hence the asset are affordable for all level of investors. In this paper, we suggest that GBM which involves randomness, volatility, and drift can help investor in making their investment decision wisely. This research shows the model is highly accurate model in forecasting stock prices and it is proven by the lower value of mean absolute percentage error (MAPE). Although it is highly accurate, we try to find the suitable volatility measurements that give the forecast value closer to the actual movement of stock prices. The result shows that by using highs-lows-close volatility, the forecast stock prices are closest to the actual prices. This volatility measurement and GBM model are suggested to the investor to forecast future prices for a maximum of two week investment.
{"title":"Surveying the best volatility measurements in stock market forecasting techniques involving small size companies in Bursa Malaysia","authors":"S. A. Z. Abidin, M. Jaafar","doi":"10.1109/SHUSER.2012.6269014","DOIUrl":"https://doi.org/10.1109/SHUSER.2012.6269014","url":null,"abstract":"This paper proposes a way to forecast the future closing price of small size companies in Bursa Malaysia by using geometric Brownian motion (GBM). Forecasting is restricted to short term investment because most of the investors aim to gain profit in short period of time. The reasons of choosing small size companies are because the asset prices are lower, hence the asset are affordable for all level of investors. In this paper, we suggest that GBM which involves randomness, volatility, and drift can help investor in making their investment decision wisely. This research shows the model is highly accurate model in forecasting stock prices and it is proven by the lower value of mean absolute percentage error (MAPE). Although it is highly accurate, we try to find the suitable volatility measurements that give the forecast value closer to the actual movement of stock prices. The result shows that by using highs-lows-close volatility, the forecast stock prices are closest to the actual prices. This volatility measurement and GBM model are suggested to the investor to forecast future prices for a maximum of two week investment.","PeriodicalId":426671,"journal":{"name":"2012 IEEE Symposium on Humanities, Science and Engineering Research","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123718473","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-06-24DOI: 10.1109/SHUSER.2012.6268825
A. N. Fadzilah, K. Dayana, U. Noor, M. Rusop
Amorphous carbon (a-C) thin films was deposited using Aerosol-Assisted CVD (AACVD) method and the properties was discussed. Flow rate of the experimental setup was varied (15, 30, 45 and 60 bubbles per minute) in order to optimize the a-C thin film characteristics and the electrical, optical and structural properties were investigated. The electrical properties was characterized by current-voltage (I-V) characteristics using Solar Simulator system and the analysis stressed on the linear (ohmic) graph for the a-C thin films. Photoresponse characteristics of the deposited a-C was highlighted when being illuminated (AM 1.5 illuminations: 100 mW/cm2, 25°C). Optical characteristics was investigated by UV-Vis-NIR spectroscope and transmittance spectrum exhibit a large transmittance value (>;85%) and high absorption coefficient value (>;106 cm-1) at the visible range of 390 to 790 nm. For structural properties, Atomic Force Microscope was used for the characterization process to obtain a-C images at atomic level.
{"title":"Opto-electrical properties of amorphous carbon thin films deposited by Aerosol-Assisted Chemical Vapor Deposition","authors":"A. N. Fadzilah, K. Dayana, U. Noor, M. Rusop","doi":"10.1109/SHUSER.2012.6268825","DOIUrl":"https://doi.org/10.1109/SHUSER.2012.6268825","url":null,"abstract":"Amorphous carbon (a-C) thin films was deposited using Aerosol-Assisted CVD (AACVD) method and the properties was discussed. Flow rate of the experimental setup was varied (15, 30, 45 and 60 bubbles per minute) in order to optimize the a-C thin film characteristics and the electrical, optical and structural properties were investigated. The electrical properties was characterized by current-voltage (I-V) characteristics using Solar Simulator system and the analysis stressed on the linear (ohmic) graph for the a-C thin films. Photoresponse characteristics of the deposited a-C was highlighted when being illuminated (AM 1.5 illuminations: 100 mW/cm2, 25°C). Optical characteristics was investigated by UV-Vis-NIR spectroscope and transmittance spectrum exhibit a large transmittance value (>;85%) and high absorption coefficient value (>;106 cm-1) at the visible range of 390 to 790 nm. For structural properties, Atomic Force Microscope was used for the characterization process to obtain a-C images at atomic level.","PeriodicalId":426671,"journal":{"name":"2012 IEEE Symposium on Humanities, Science and Engineering Research","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126535855","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-06-24DOI: 10.1109/SHUSER.2012.6268868
W. Rahman, S. Sudin, S. N. Din
Natural fibers become most important reinforcement materials for commercial thermoplastic as it can easily biodegraded, high specific strength, abundant, renewable and easy processing. In this study, a partially biodegradable composite was prepared by melt-mixing of low density polyethylene (LDPE) with Pandanus amaryllifolius fiber (PAF). The effect of the PAF content on composite properties was investigated. Result demonstrated that the increasing of PAF content increased the density and water absorption of the composite. Tensile modulus of the composite also increase from 10.3 MPa (PAF content = 0 wt%) to 121 MPa (PAF content = 50 wt%). However the increasing of PAF content also resulted in a decreasing of tensile strength, impact strength and elongation at break of the composite.
{"title":"Physical and mechanical properties of Pandanus amaryllifolius fiber reinforced low density polyethylene composite for packaging application","authors":"W. Rahman, S. Sudin, S. N. Din","doi":"10.1109/SHUSER.2012.6268868","DOIUrl":"https://doi.org/10.1109/SHUSER.2012.6268868","url":null,"abstract":"Natural fibers become most important reinforcement materials for commercial thermoplastic as it can easily biodegraded, high specific strength, abundant, renewable and easy processing. In this study, a partially biodegradable composite was prepared by melt-mixing of low density polyethylene (LDPE) with Pandanus amaryllifolius fiber (PAF). The effect of the PAF content on composite properties was investigated. Result demonstrated that the increasing of PAF content increased the density and water absorption of the composite. Tensile modulus of the composite also increase from 10.3 MPa (PAF content = 0 wt%) to 121 MPa (PAF content = 50 wt%). However the increasing of PAF content also resulted in a decreasing of tensile strength, impact strength and elongation at break of the composite.","PeriodicalId":426671,"journal":{"name":"2012 IEEE Symposium on Humanities, Science and Engineering Research","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125294711","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-06-24DOI: 10.1109/SHUSER.2012.6268863
N. A. Yahya, M. Awang, A. Ibrahim
A new embedded 5(4) pair implicit 2-step hybrid method for solving second-order differential equation of the form y" = f (x, y) is proposed in this paper. The new method is constructed by introducing single diagonal element in the order conditions. The order conditions which contain the coefficients of the method are used in the error constant to determine the free parameter in fourth and fifth order implicit 2-step hybrid method. The stability analysis is determined by the interval of periodicity and the interval of absolute stability. Some numerical experiments are tested upon and the numerical results showed that the new method is more accurate compared with the implicit 2-step hybrid method of order four and order five.
本文提出了一种新的求解形式为y”= f (x, y)二阶微分方程的嵌入式5(4)对隐式两步混合方法。该方法通过在有序条件下引入单对角元来构造。在四阶和五阶隐式两步混合方法中，误差常数中使用包含该方法系数的阶条件来确定自由参数。稳定性分析由周期区间和绝对稳定区间决定。数值实验结果表明，与隐式四阶和五阶两步混合方法相比，该方法具有更高的精度。
{"title":"Embedded 5(4) pair implicit 2-step hybrid method for solving special second-order initial value problems","authors":"N. A. Yahya, M. Awang, A. Ibrahim","doi":"10.1109/SHUSER.2012.6268863","DOIUrl":"https://doi.org/10.1109/SHUSER.2012.6268863","url":null,"abstract":"A new embedded 5(4) pair implicit 2-step hybrid method for solving second-order differential equation of the form y\" = f (x, y) is proposed in this paper. The new method is constructed by introducing single diagonal element in the order conditions. The order conditions which contain the coefficients of the method are used in the error constant to determine the free parameter in fourth and fifth order implicit 2-step hybrid method. The stability analysis is determined by the interval of periodicity and the interval of absolute stability. Some numerical experiments are tested upon and the numerical results showed that the new method is more accurate compared with the implicit 2-step hybrid method of order four and order five.","PeriodicalId":426671,"journal":{"name":"2012 IEEE Symposium on Humanities, Science and Engineering Research","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114880551","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-06-24DOI: 10.1109/SHUSER.2012.6268824
N. S. M. Sauki, M. Rahim, S. H. Herman, M. Mahmood
The structural, and electrical properties of ZnO thin films deposited by sol-gel spin coating technique, onto polytetrafluoroethylene (Teflon) and glass substrates have been investigated. 0.4M sol were prepared by using Zinc acetate dehydrate as precursor, monoethanolamine as stabilizer and 2-methoxyethanol as solvent. The thin films were annealed at 200°C, 250°C and 300°C. This annealing process was performed in every layer. Electrical characterization shows the conductivity of the films deposited onto Teflon substrates that annealed at 200°C, 250°C and 300°C were around 0.176, 0.0988, and 0.0952 S cm-1 respectively. On the other hand, for the thin films deposited on glass substrates, these values are 0.187, 0.139 and 0.126 S cm-1 for similar variation in the annealing temperature. The conductivity of the ZnO thin films on glass substrate was higher than those on Teflon substrates. FESEM images confirmed that microstructure of the thin films on both substrate consists of nanoparticles.
研究了溶胶-凝胶自旋镀膜技术在聚四氟乙烯(Teflon)和玻璃基底上沉积ZnO薄膜的结构和电学性能。以脱水乙酸锌为前驱体，单乙醇胺为稳定剂，2-甲氧基乙醇为溶剂，制备了0.4M溶胶。薄膜分别在200°C、250°C和300°C退火。在每一层都进行了这种退火过程。电学表征表明，在200°C、250°C和300°C退火的Teflon衬底上沉积的薄膜的电导率分别约为0.176、0.0988和0.0952 S cm-1。另一方面，对于沉积在玻璃衬底上的薄膜，对于退火温度的相似变化，这些值分别为0.187,0.139和0.126 S cm-1。ZnO薄膜在玻璃基板上的电导率高于在聚四氟乙烯基板上的电导率。FESEM图像证实，两种衬底上的薄膜微观结构均由纳米颗粒组成。
{"title":"Physical and electrical characteristics of low-temperature annealed spin coated zinc oxide thin films on Teflon substrates","authors":"N. S. M. Sauki, M. Rahim, S. H. Herman, M. Mahmood","doi":"10.1109/SHUSER.2012.6268824","DOIUrl":"https://doi.org/10.1109/SHUSER.2012.6268824","url":null,"abstract":"The structural, and electrical properties of ZnO thin films deposited by sol-gel spin coating technique, onto polytetrafluoroethylene (Teflon) and glass substrates have been investigated. 0.4M sol were prepared by using Zinc acetate dehydrate as precursor, monoethanolamine as stabilizer and 2-methoxyethanol as solvent. The thin films were annealed at 200°C, 250°C and 300°C. This annealing process was performed in every layer. Electrical characterization shows the conductivity of the films deposited onto Teflon substrates that annealed at 200°C, 250°C and 300°C were around 0.176, 0.0988, and 0.0952 S cm-1 respectively. On the other hand, for the thin films deposited on glass substrates, these values are 0.187, 0.139 and 0.126 S cm-1 for similar variation in the annealing temperature. The conductivity of the ZnO thin films on glass substrate was higher than those on Teflon substrates. FESEM images confirmed that microstructure of the thin films on both substrate consists of nanoparticles.","PeriodicalId":426671,"journal":{"name":"2012 IEEE Symposium on Humanities, Science and Engineering Research","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114721784","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-06-24DOI: 10.1109/SHUSER.2012.6268780
A. Lokman, K. K. Ishak, F. H. A. Razak, A. A. Aziz
Kansei Engineering has been successfully used as product design technology inducing human emotion in its quality value. It has in its perspective that Kansei is unique for different domain and that it is unique for different target user group, and results from the evaluation of human Kansei have uniqueness in different cultural races and demographical background. Although the success is proven, the technology has shortcoming when there is a need to build universal design for universal target user. Therefore, we need to have a non-verbal cross-culture emotion measurement tool which could enhance the capability of K.E. in the measurement of universal Kansei across cultures. This study aims to investigate the feasibility of using a nonverbal, animation based emotion measurement instrument called PrEmo to measure Kansei as a solution to universal Kansei in a cross-cultural environment. The feasibility was analyzed by performing a comparative analysis of Kansei structure with the use of PrEmo with two different cultural races. 10 websites with significant visual design differences were used as stimuli in the evaluation procedure involving 30 subjects. The resulted Kansei structure from the comparative study shows that there is encouraging results to show that PrEmo could be used to measure Kansei. Future research is required to cater the measurement of Kansei that are not limited to the 12 general emotions as suggested in PrEmo.
{"title":"The feasibility of PrEmo in cross-cultural Kansei measurement","authors":"A. Lokman, K. K. Ishak, F. H. A. Razak, A. A. Aziz","doi":"10.1109/SHUSER.2012.6268780","DOIUrl":"https://doi.org/10.1109/SHUSER.2012.6268780","url":null,"abstract":"Kansei Engineering has been successfully used as product design technology inducing human emotion in its quality value. It has in its perspective that Kansei is unique for different domain and that it is unique for different target user group, and results from the evaluation of human Kansei have uniqueness in different cultural races and demographical background. Although the success is proven, the technology has shortcoming when there is a need to build universal design for universal target user. Therefore, we need to have a non-verbal cross-culture emotion measurement tool which could enhance the capability of K.E. in the measurement of universal Kansei across cultures. This study aims to investigate the feasibility of using a nonverbal, animation based emotion measurement instrument called PrEmo to measure Kansei as a solution to universal Kansei in a cross-cultural environment. The feasibility was analyzed by performing a comparative analysis of Kansei structure with the use of PrEmo with two different cultural races. 10 websites with significant visual design differences were used as stimuli in the evaluation procedure involving 30 subjects. The resulted Kansei structure from the comparative study shows that there is encouraging results to show that PrEmo could be used to measure Kansei. Future research is required to cater the measurement of Kansei that are not limited to the 12 general emotions as suggested in PrEmo.","PeriodicalId":426671,"journal":{"name":"2012 IEEE Symposium on Humanities, Science and Engineering Research","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124297692","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-06-24DOI: 10.1109/SHUSER.2012.6268874
S. Mondal, D. Chakraborty, R. Kar, D. Mandal, S. Ghoshal
This paper presents an optimal design of linear phase digital high pass finite impulse response (FIR) filter using Novel Particle Swarm Optimization (NPSO). NPSO is an improved particle swarm optimization (PSO) that proposes a new definition for the velocity vector and swarm updating and hence the solution quality is improved. The inertia weight has been modified in the PSO to enhance its search capability that leads to a higher probability of obtaining the global optimal solution. The key feature of the applied modified inertia weight mechanism is to monitor the weights of particles, which linearly decrease in general applications. In the design process, the filter length, pass band and stop band frequencies, feasible pass band and stop band ripple sizes are specified. FIR filter design is a multi-modal optimization problem. Evolutionary algorithms like real code genetic algorithm (RGA), particle swarm optimization (PSO), differential evolution (DE), and the novel particle swarm optimization (NPSO) have been used in this work for the design of linear phase FIR high pass (HP) filter. A comparison of simulation results reveals the optimization efficacy of the algorithm over the prevailing optimization techniques for the solution of the multimodal, non-differentiable, highly non-linear, and constrained FIR filter design problems.
{"title":"Novel particle swarm optimization for high pass FIR filter design","authors":"S. Mondal, D. Chakraborty, R. Kar, D. Mandal, S. Ghoshal","doi":"10.1109/SHUSER.2012.6268874","DOIUrl":"https://doi.org/10.1109/SHUSER.2012.6268874","url":null,"abstract":"This paper presents an optimal design of linear phase digital high pass finite impulse response (FIR) filter using Novel Particle Swarm Optimization (NPSO). NPSO is an improved particle swarm optimization (PSO) that proposes a new definition for the velocity vector and swarm updating and hence the solution quality is improved. The inertia weight has been modified in the PSO to enhance its search capability that leads to a higher probability of obtaining the global optimal solution. The key feature of the applied modified inertia weight mechanism is to monitor the weights of particles, which linearly decrease in general applications. In the design process, the filter length, pass band and stop band frequencies, feasible pass band and stop band ripple sizes are specified. FIR filter design is a multi-modal optimization problem. Evolutionary algorithms like real code genetic algorithm (RGA), particle swarm optimization (PSO), differential evolution (DE), and the novel particle swarm optimization (NPSO) have been used in this work for the design of linear phase FIR high pass (HP) filter. A comparison of simulation results reveals the optimization efficacy of the algorithm over the prevailing optimization techniques for the solution of the multimodal, non-differentiable, highly non-linear, and constrained FIR filter design problems.","PeriodicalId":426671,"journal":{"name":"2012 IEEE Symposium on Humanities, Science and Engineering Research","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122171868","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-06-24DOI: 10.1109/SHUSER.2012.6268896
M. Musa, M. H. Mamat, M. H. Abdullah, M. F. Malek, A. Nor, N. A. Rasheid, U. Noor, M. Rusop
Nb-doped TiO2 thin films have been successfully prepared using liquid phase solution method. For the first time, Nb-doped sol-gel has been combined with commercially available TiO2 nanopowder (Degussa P25) for preparing Nb-doped TiO2 photoanode for DSSC application. EDX analysis confirms the presence of Nb in the thin films. Nb-doped TiO2 sample showed improvement in term of electrical resistivity characteristic compared to undoped sample with 8.0 at% Nb-doped sample having the lowest resistivity value. When utilized as photoanode in DSSC, the energy conversion efficiency showed an improvement of 81.3% compared to the undoped one.
{"title":"A modified sol-gel method for preparing nanostructured Nb-doped TiO2 DSSC photoanode","authors":"M. Musa, M. H. Mamat, M. H. Abdullah, M. F. Malek, A. Nor, N. A. Rasheid, U. Noor, M. Rusop","doi":"10.1109/SHUSER.2012.6268896","DOIUrl":"https://doi.org/10.1109/SHUSER.2012.6268896","url":null,"abstract":"Nb-doped TiO2 thin films have been successfully prepared using liquid phase solution method. For the first time, Nb-doped sol-gel has been combined with commercially available TiO2 nanopowder (Degussa P25) for preparing Nb-doped TiO2 photoanode for DSSC application. EDX analysis confirms the presence of Nb in the thin films. Nb-doped TiO2 sample showed improvement in term of electrical resistivity characteristic compared to undoped sample with 8.0 at% Nb-doped sample having the lowest resistivity value. When utilized as photoanode in DSSC, the energy conversion efficiency showed an improvement of 81.3% compared to the undoped one.","PeriodicalId":426671,"journal":{"name":"2012 IEEE Symposium on Humanities, Science and Engineering Research","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127759041","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-06-24DOI: 10.1109/SHUSER.2012.6268782
S. Hew, Sim-Hui Tee
Computational tools are indispensable in the genetic engineering today. This research employs computational analysis on microRNAs which are targeting at the PTEN gene. This study aims to analyze the implication of microRNAs in the expression of PTEN which is leading to tumorigenesis. The analysis of microRNAs sheds light on the regulatory mechanism of PTEN in cancer development.
{"title":"Computational analysis of PTEN-targeting microRNAs","authors":"S. Hew, Sim-Hui Tee","doi":"10.1109/SHUSER.2012.6268782","DOIUrl":"https://doi.org/10.1109/SHUSER.2012.6268782","url":null,"abstract":"Computational tools are indispensable in the genetic engineering today. This research employs computational analysis on microRNAs which are targeting at the PTEN gene. This study aims to analyze the implication of microRNAs in the expression of PTEN which is leading to tumorigenesis. The analysis of microRNAs sheds light on the regulatory mechanism of PTEN in cancer development.","PeriodicalId":426671,"journal":{"name":"2012 IEEE Symposium on Humanities, Science and Engineering Research","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115773489","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-06-24DOI: 10.1109/SHUSER.2012.6268818
A. S. Shafie, I. A. Mohtar, S. Masrom, N. Ahmad
Neural network has been used extensively for classification and many real world applications. The most commonly used neural network is multilayer perceptron with backpropagation (BP) algorithm. However the major problem of this algorithm is slow convergence rate and trap to local minima. The convergence is dependent on network parameters such as learning rate, momentum term and slope of activation function as well as its error function. This study proposes a New Improved BP algorithm which applies adaptive activation function using arctangent function in input-to-hidden layer and sigmoid logistic function in hidden-to-output layer. The efficiency and accuracy of the new improved method have been implemented and tested on two benchmark datasets: XOR and Balloon. The results show that the proposed method improved the convergence speed. However the classification accuracy is not very encouraging.
{"title":"Backpropagation neural network with new improved error function and activation function for classification problem","authors":"A. S. Shafie, I. A. Mohtar, S. Masrom, N. Ahmad","doi":"10.1109/SHUSER.2012.6268818","DOIUrl":"https://doi.org/10.1109/SHUSER.2012.6268818","url":null,"abstract":"Neural network has been used extensively for classification and many real world applications. The most commonly used neural network is multilayer perceptron with backpropagation (BP) algorithm. However the major problem of this algorithm is slow convergence rate and trap to local minima. The convergence is dependent on network parameters such as learning rate, momentum term and slope of activation function as well as its error function. This study proposes a New Improved BP algorithm which applies adaptive activation function using arctangent function in input-to-hidden layer and sigmoid logistic function in hidden-to-output layer. The efficiency and accuracy of the new improved method have been implemented and tested on two benchmark datasets: XOR and Balloon. The results show that the proposed method improved the convergence speed. However the classification accuracy is not very encouraging.","PeriodicalId":426671,"journal":{"name":"2012 IEEE Symposium on Humanities, Science and Engineering Research","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126460011","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：