Pub Date : 2020-05-15DOI: 10.23953/cloud.ijacsit.461
Wang Shuangao, Liu Yi, R. Padmanaban, M. Shamsudeen, R. Subalakshmi
Artificial neural network is widely used in the financial time series, but Long short-term memory (LSTM) neural network is rarely used in the futures market in China. In this paper, the LSTM neural network is studied by using futures data. The daily trading data of four groups of futures such as silver, copper, lithium and coking coal from December 2014 to December 2018 are used as the training object to make short-term prediction of the closing price. By comparing the Back Propagation (BP) neural network, general multi-layer LSTM neural network, and using the attention mechanism optimization LSTM contrast test, the result of the experiment shows that the futures price trend forecast time sequence, attention mechanism to promote significant effect of time sequence, and LSTM combined effect, by adjusting the parameters setting, using the improved LSTM neural network for time series prediction accuracy is higher, better generalization ability.
{"title":"Comparison of Back Propagation, Long Short-Term Memory (LSTM), Attention-Based LSTM Neural Networks Application in Futures Market of China using R Programming","authors":"Wang Shuangao, Liu Yi, R. Padmanaban, M. Shamsudeen, R. Subalakshmi","doi":"10.23953/cloud.ijacsit.461","DOIUrl":"https://doi.org/10.23953/cloud.ijacsit.461","url":null,"abstract":"Artificial neural network is widely used in the financial time series, but Long short-term memory (LSTM) neural network is rarely used in the futures market in China. In this paper, the LSTM neural network is studied by using futures data. The daily trading data of four groups of futures such as silver, copper, lithium and coking coal from December 2014 to December 2018 are used as the training object to make short-term prediction of the closing price. By comparing the Back Propagation (BP) neural network, general multi-layer LSTM neural network, and using the attention mechanism optimization LSTM contrast test, the result of the experiment shows that the futures price trend forecast time sequence, attention mechanism to promote significant effect of time sequence, and LSTM combined effect, by adjusting the parameters setting, using the improved LSTM neural network for time series prediction accuracy is higher, better generalization ability.","PeriodicalId":90853,"journal":{"name":"International journal of advanced computer science","volume":"6 1","pages":"101-114"},"PeriodicalIF":0.0,"publicationDate":"2020-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43917349","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 : 2016-07-22DOI: 10.23953/CLOUD.IJACSIT.235
Akrati Sharma, Sanjiv Sharma
Cloud computing become most adoptable technology over the past few years, it is widespread for both at organizational level or for the person who use the services that are offered in the cloud. There are several technocrats currently researched on cloud related issues and soon cloud represents the modern computing. The cloud gave the prospect for the enterprise and allowing them to center on their work by providing hardware and software solution without developing them own. Now a day the database has also moved to cloud computing so we will look into the fine points of database as a service and it’s servicing. While storing data on cloud there is a need to balance the load on datacenters because if user base always sends request on single data center then it becomes overloaded so load balancing techniques are applied to manage this problem. To manage geographic distribution in terms of computing servers and data workloads a tool termed as CloudAnalyst is used which is based on cloudsim technique. CloudAnalyst helps developers with the vision of distributing applications among cloud infrastructures. Currently tool having three algorithms for load balancing round robin, throttled load balancer, equally spread current execution and the proposed algorithm is weighted round robin which works better as comparison to round robin in various aspects.
{"title":"Analysis of Different Methods for Measuring the Performance of Database on Cloud Environment","authors":"Akrati Sharma, Sanjiv Sharma","doi":"10.23953/CLOUD.IJACSIT.235","DOIUrl":"https://doi.org/10.23953/CLOUD.IJACSIT.235","url":null,"abstract":"Cloud computing become most adoptable technology over the past few years, it is widespread for both at organizational level or for the person who use the services that are offered in the cloud. There are several technocrats currently researched on cloud related issues and soon cloud represents the modern computing. The cloud gave the prospect for the enterprise and allowing them to center on their work by providing hardware and software solution without developing them own. Now a day the database has also moved to cloud computing so we will look into the fine points of database as a service and it’s servicing. While storing data on cloud there is a need to balance the load on datacenters because if user base always sends request on single data center then it becomes overloaded so load balancing techniques are applied to manage this problem. To manage geographic distribution in terms of computing servers and data workloads a tool termed as CloudAnalyst is used which is based on cloudsim technique. CloudAnalyst helps developers with the vision of distributing applications among cloud infrastructures. Currently tool having three algorithms for load balancing round robin, throttled load balancer, equally spread current execution and the proposed algorithm is weighted round robin which works better as comparison to round robin in various aspects.","PeriodicalId":90853,"journal":{"name":"International journal of advanced computer science","volume":"5 1","pages":"83-100"},"PeriodicalIF":0.0,"publicationDate":"2016-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"68778893","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 : 2016-02-09DOI: 10.23953/CLOUD.IJACSIT.234
B. Nagarajan, G. Venkatesan, C. S. Kumar
Wireless scheduling algorithms for the download of a single cell that can maximize the asymptotic decay rate of the queue-overflow probability as the overflow threshold approaches infinity. We first derive an upper bound on the decay rate of the queue-overflow probability over all scheduling policies. Specifically, we focus on the class of “α - algorithms,” the base station picks the user for service at each time that has the largest product of the transmission rate multiplied by the backlog raised to the power α. The α-algorithms arbitrarily achieve the highest decay rate of the queue-overflow probability. We design a scheduling algorithm that is both close to optimal in terms of the asymptotic decay rate of the overflow probability and to maintain small queue-overflow probabilities over queue-length ranges of practical interest.
{"title":"A Study of Scheduling Algorithms to Maintain Small Overflow Probability in Cellular Networks with a Single Cell","authors":"B. Nagarajan, G. Venkatesan, C. S. Kumar","doi":"10.23953/CLOUD.IJACSIT.234","DOIUrl":"https://doi.org/10.23953/CLOUD.IJACSIT.234","url":null,"abstract":"Wireless scheduling algorithms for the download of a single cell that can maximize the asymptotic decay rate of the queue-overflow probability as the overflow threshold approaches infinity. We first derive an upper bound on the decay rate of the queue-overflow probability over all scheduling policies. Specifically, we focus on the class of “α - algorithms,” the base station picks the user for service at each time that has the largest product of the transmission rate multiplied by the backlog raised to the power α. The α-algorithms arbitrarily achieve the highest decay rate of the queue-overflow probability. We design a scheduling algorithm that is both close to optimal in terms of the asymptotic decay rate of the overflow probability and to maintain small queue-overflow probabilities over queue-length ranges of practical interest.","PeriodicalId":90853,"journal":{"name":"International journal of advanced computer science","volume":"41 1","pages":"78-82"},"PeriodicalIF":0.0,"publicationDate":"2016-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"68778711","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}
In recent years, uncertain textual data has become ubiquitous because of latest technologies of data collect. As the existing technologies can only collect data in an imprecise way. So in the given paper, we propose frequent pattern mining technique for mining termsets from uncertain textual data. in the said technique, we have conducted a study on uncertain textual data with Karnaugh Map concept. In fact the contribution of given paper is three manifolds. Firstly, we review existing method of finding frequent termset form document data. Secondly a new method UTDKM (Uncertain Textual Data using Karnaugh Map) is proposed for finding frequent termset from uncertain textual data, and lastly, we carried experiments to evaluate the performance of proposed method. The experimental results demonstrate that UTDKM method is better for mining frequent termset in comparison to existing methods.
{"title":"Karnaugh Map Approach for Mining Frequent Termset from Uncertain Textual Data","authors":"D. Rajput, R. S. Thakur, G. Thakur","doi":"10.9734/BJMCS/2014/6023","DOIUrl":"https://doi.org/10.9734/BJMCS/2014/6023","url":null,"abstract":"In recent years, uncertain textual data has become ubiquitous because of latest technologies of data collect. As the existing technologies can only collect data in an imprecise way. So in the given paper, we propose frequent pattern mining technique for mining termsets from uncertain textual data. in the said technique, we have conducted a study on uncertain textual data with Karnaugh Map concept. In fact the contribution of given paper is three manifolds. Firstly, we review existing method of finding frequent termset form document data. Secondly a new method UTDKM (Uncertain Textual Data using Karnaugh Map) is proposed for finding frequent termset from uncertain textual data, and lastly, we carried experiments to evaluate the performance of proposed method. The experimental results demonstrate that UTDKM method is better for mining frequent termset in comparison to existing methods.","PeriodicalId":90853,"journal":{"name":"International journal of advanced computer science","volume":"5 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2014-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"71185894","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}
In this paper, we have considered automatic locating of semantic errors and to achieve this purpose, a method has been suggested based on the input, which is the most important element in error detection. In the proposed method, successful entries have been developed based on unsuccessful entries by finding route limitation dynamically and using determinant limitation debugging technique and by comparing the implementation route for both unsuccessful and successful inputs and applying genetic algorithm, the error location will be identified in the software. The results of our studies, which are based on our purposed approach, have been compared with the results of other studies and it has been observed that our suggested method has a better function regarding the percentage of the errors discovered.
{"title":"Software Debugging By Developing and Comparing Very Close Successful Inputs with Failure Inducing Unsuccessful Inputs","authors":"F. Dashti, Parvaneh Pour Mohammad","doi":"10.1166/JCIES.2013.1050","DOIUrl":"https://doi.org/10.1166/JCIES.2013.1050","url":null,"abstract":"In this paper, we have considered automatic locating of semantic errors and to achieve this purpose, a method has been suggested based on the input, which is the most important element in error detection. In the proposed method, successful entries have been developed based on unsuccessful entries by finding route limitation dynamically and using determinant limitation debugging technique and by comparing the implementation route for both unsuccessful and successful inputs and applying genetic algorithm, the error location will be identified in the software. The results of our studies, which are based on our purposed approach, have been compared with the results of other studies and it has been observed that our suggested method has a better function regarding the percentage of the errors discovered.","PeriodicalId":90853,"journal":{"name":"International journal of advanced computer science","volume":"4 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"64485639","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}
Narine Manukyan, Margaret J Eppstein, Jeffrey D Horbar, Kathleen A Leahy, Michael J Kenny, Shreya Mukherjee, Donna M Rizzo
We introduce a new method for exploratory analysis of large data sets with time-varying features, where the aim is to automatically discover novel relationships between features (over some time period) that are predictive of any of a number of time-varying outcomes (over some other time period). Using a genetic algorithm, we co-evolve (i) a subset of predictive features, (ii) which attribute will be predicted (iii) the time period over which to assess the predictive features, and (iv) the time period over which to assess the predicted attribute. After validating the method on 15 synthetic test problems, we used the approach for exploratory analysis of a large healthcare network data set. We discovered a strong association, with 100% sensitivity, between hospital participation in multi-institutional quality improvement collaboratives during or before 2002, and changes in the risk-adjusted rates of mortality and morbidity observed after a 1-2 year lag. The proposed approach is a potentially powerful and general tool for exploratory analysis of a wide range of time-series data sets.
{"title":"Exploratory Analysis in Time-Varying Data Sets: a Healthcare Network Application.","authors":"Narine Manukyan, Margaret J Eppstein, Jeffrey D Horbar, Kathleen A Leahy, Michael J Kenny, Shreya Mukherjee, Donna M Rizzo","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>We introduce a new method for exploratory analysis of large data sets with time-varying features, where the aim is to automatically discover novel relationships between features (over some time period) that are predictive of any of a number of time-varying outcomes (over some other time period). Using a genetic algorithm, we co-evolve (i) a subset of predictive features, (ii) which attribute will be predicted (iii) the time period over which to assess the predictive features, and (iv) the time period over which to assess the predicted attribute. After validating the method on 15 synthetic test problems, we used the approach for exploratory analysis of a large healthcare network data set. We discovered a strong association, with 100% sensitivity, between hospital participation in multi-institutional quality improvement collaboratives during or before 2002, and changes in the risk-adjusted rates of mortality and morbidity observed after a 1-2 year lag. The proposed approach is a potentially powerful and general tool for exploratory analysis of a wide range of time-series data sets.</p>","PeriodicalId":90853,"journal":{"name":"International journal of advanced computer science","volume":"3 7","pages":"322-329"},"PeriodicalIF":0.0,"publicationDate":"2013-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4319218/pdf/nihms627602.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"33370465","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Porkodi Chinniah, Nagarathnam Muthusamy, A. Ramalingam
Factorization of large integers is a significant mathematical problem with practical applications to public key cryptography. It is considered to be a part of cryptanalysis. The progress in factoring tends to weaken the existing efficient public key cryptosystems. Several algorithms such as trial division, Pollard rho, Pollard p-1, Quadratic sieve, Lenstra's elliptic curve and Number field sieve are available to solve the integer factorization problem. In this paper a special purpose factorization algorithm is proposed to find the factors of a composite number which is the product of two primes. The running time complexity of the proposed scheme is discussed. The efficiency of the scheme is proved theoretically.
{"title":"A special purpose integer factorization algorithm","authors":"Porkodi Chinniah, Nagarathnam Muthusamy, A. Ramalingam","doi":"10.1145/2393216.2393246","DOIUrl":"https://doi.org/10.1145/2393216.2393246","url":null,"abstract":"Factorization of large integers is a significant mathematical problem with practical applications to public key cryptography. It is considered to be a part of cryptanalysis. The progress in factoring tends to weaken the existing efficient public key cryptosystems. Several algorithms such as trial division, Pollard rho, Pollard p-1, Quadratic sieve, Lenstra's elliptic curve and Number field sieve are available to solve the integer factorization problem. In this paper a special purpose factorization algorithm is proposed to find the factors of a composite number which is the product of two primes. The running time complexity of the proposed scheme is discussed. The efficiency of the scheme is proved theoretically.","PeriodicalId":90853,"journal":{"name":"International journal of advanced computer science","volume":"4 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2012-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1145/2393216.2393246","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"64144997","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}
A potential flow model is used to study the unsteady flow past two airfoils in configuration, each of which is suddenly set into motion. The airfoil bound vortices are modeled using lumped vortex elements and the wake behind the airfoil is modeled by discrete vortices. This consists of solving a steady state flow problem at each time-step where unsteadiness is incorporated through the “zero normal flow on a solid surface” boundary condition at every time instant. Additionally, along with the “zero normal flow on a solid surface” boundary condition Kelvin’s condition is used to compute the strength of the latest wake vortex shed from the trailing edge of the airfoil. Location of the wake vortices is updated at each time-step to get the wake shape at each time instant. Results are presented to show the effect of airfoil-airfoil interaction and airfoil-wake interaction on the aerodynamic characteristics of each airfoil.
{"title":"Unsteady Aerodynamics of Multiple Airfoils in Configuration","authors":"H. Aziz, R. Mukherjee","doi":"10.2514/6.2011-3523","DOIUrl":"https://doi.org/10.2514/6.2011-3523","url":null,"abstract":"A potential flow model is used to study the unsteady flow past two airfoils in configuration, each of which is suddenly set into motion. The airfoil bound vortices are modeled using lumped vortex elements and the wake behind the airfoil is modeled by discrete vortices. This consists of solving a steady state flow problem at each time-step where unsteadiness is incorporated through the “zero normal flow on a solid surface” boundary condition at every time instant. Additionally, along with the “zero normal flow on a solid surface” boundary condition Kelvin’s condition is used to compute the strength of the latest wake vortex shed from the trailing edge of the airfoil. Location of the wake vortices is updated at each time-step to get the wake shape at each time instant. Results are presented to show the effect of airfoil-airfoil interaction and airfoil-wake interaction on the aerodynamic characteristics of each airfoil.","PeriodicalId":90853,"journal":{"name":"International journal of advanced computer science","volume":"2 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2010-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.2514/6.2011-3523","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"69061411","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 : 2010-07-09DOI: 10.1109/ICCSIT.2010.5565109
Shuguang Zhang, Ming Lu
By analyzing hydrogeological conditions of panxi coal, the coupling mathematical model of heat-transfer is developed in surrounding rock.Temperature field and seepage field distribution of fracture rock is described by using heat-transfer and seepage differential equations. Combined with boundary condition and parameters, the numerical solution is obtained by using numerical software. The results of numerical simulation show that the temperature of surrounding rock change under the influence of the seepage. Because of the temperature difference between the groundwater and the surrounding rock, heat axchange will occur on the coupling section. Eventually the temperature of water is similar to the surrounding rock and form the balance area of heat exchange. This indicated that heat transfer accompany the process of seeapge. At the same time, the balance area of heat exchange will move following leakage, and along with the seepage speed increasing, the balance area of the scope will enlarge. With the existence of the blance area, it becomes the watershed of the temperature vector change.
{"title":"Notice of RetractionFluid-solid coupling numerical simulation of temperature field of roadway surrounding rock in water-bearing formation","authors":"Shuguang Zhang, Ming Lu","doi":"10.1109/ICCSIT.2010.5565109","DOIUrl":"https://doi.org/10.1109/ICCSIT.2010.5565109","url":null,"abstract":"By analyzing hydrogeological conditions of panxi coal, the coupling mathematical model of heat-transfer is developed in surrounding rock.Temperature field and seepage field distribution of fracture rock is described by using heat-transfer and seepage differential equations. Combined with boundary condition and parameters, the numerical solution is obtained by using numerical software. The results of numerical simulation show that the temperature of surrounding rock change under the influence of the seepage. Because of the temperature difference between the groundwater and the surrounding rock, heat axchange will occur on the coupling section. Eventually the temperature of water is similar to the surrounding rock and form the balance area of heat exchange. This indicated that heat transfer accompany the process of seeapge. At the same time, the balance area of heat exchange will move following leakage, and along with the seepage speed increasing, the balance area of the scope will enlarge. With the existence of the blance area, it becomes the watershed of the temperature vector change.","PeriodicalId":90853,"journal":{"name":"International journal of advanced computer science","volume":"7 1","pages":"440-442"},"PeriodicalIF":0.0,"publicationDate":"2010-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/ICCSIT.2010.5565109","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62304643","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：