Pub Date : 2022-03-02DOI: 10.1109/dchpc55044.2022.9732101
Mohammad Taghi Faghihi Nezhad, Mahdi Rezaei
The use of artificial intelligence-based models have shown that the stock market is predictable despite its uncertainty and unstable nature. The most important challenge of the proposed models in the stock market is the accuracy of the results and increasing the forecasting efficiency. To overcome this challenge, this paper employs ensemble learning (EL) model using intelligence-based learners and metaheuristic optimization methods to maximize the improvement of forecasting performance. The multiplicity of inputs in the prediction model reduces the speed of execution and increases complexity. The proposed model, with feature selection, increases the accuracy and use as a real-time model. Genetic algorithm (GA) and particle swarm optimization (PSO) technique are used to optimize the aggregation results of the base learners. The evaluation results of stock market dataset show that the proposed model can overcome the market fluctuations and can be used as a reliable model.
{"title":"Stock price prediction using intelligent models, Ensemble Learning and feature selection","authors":"Mohammad Taghi Faghihi Nezhad, Mahdi Rezaei","doi":"10.1109/dchpc55044.2022.9732101","DOIUrl":"https://doi.org/10.1109/dchpc55044.2022.9732101","url":null,"abstract":"The use of artificial intelligence-based models have shown that the stock market is predictable despite its uncertainty and unstable nature. The most important challenge of the proposed models in the stock market is the accuracy of the results and increasing the forecasting efficiency. To overcome this challenge, this paper employs ensemble learning (EL) model using intelligence-based learners and metaheuristic optimization methods to maximize the improvement of forecasting performance. The multiplicity of inputs in the prediction model reduces the speed of execution and increases complexity. The proposed model, with feature selection, increases the accuracy and use as a real-time model. Genetic algorithm (GA) and particle swarm optimization (PSO) technique are used to optimize the aggregation results of the base learners. The evaluation results of stock market dataset show that the proposed model can overcome the market fluctuations and can be used as a reliable model.","PeriodicalId":59014,"journal":{"name":"高性能计算技术","volume":"14 1","pages":"15-25"},"PeriodicalIF":0.0,"publicationDate":"2022-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82138198","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 : 2022-03-02DOI: 10.1109/dchpc55044.2022.9732107
T. Gandomani, Maedeh Dashti, Mina Ziaei Nafchi
The software cost estimation (SCE) problem is one of the major challenges in software engineering. Inaccurate cost and time estimation in a software project may lead to devastating damage to software companies. To deal with this issue, software researchers have made significant efforts during recent years to improve and modify the available SCE models, one widely-used model of which is the Constructive Cost Model (COCOMO). This research aims to optimize the coefficients of a standard COCOMO model for SCE by combining genetic algorithm (GA) and environmental adaptation (EA) methods. The results indicate that the EA algorithm can solve the divergence issue of the genetic algorithm and optimize the coefficients of the COCOMO model as well. Moreover, the accuracy of the SCE in the case of combining GA and EA algorithms is 8% higher than when these algorithms are separately adopted.
{"title":"Hybrid Genetic-Environmental Adaptation Algorithm to Improve Parameters of COCOMO for Software Cost Estimation","authors":"T. Gandomani, Maedeh Dashti, Mina Ziaei Nafchi","doi":"10.1109/dchpc55044.2022.9732107","DOIUrl":"https://doi.org/10.1109/dchpc55044.2022.9732107","url":null,"abstract":"The software cost estimation (SCE) problem is one of the major challenges in software engineering. Inaccurate cost and time estimation in a software project may lead to devastating damage to software companies. To deal with this issue, software researchers have made significant efforts during recent years to improve and modify the available SCE models, one widely-used model of which is the Constructive Cost Model (COCOMO). This research aims to optimize the coefficients of a standard COCOMO model for SCE by combining genetic algorithm (GA) and environmental adaptation (EA) methods. The results indicate that the EA algorithm can solve the divergence issue of the genetic algorithm and optimize the coefficients of the COCOMO model as well. Moreover, the accuracy of the SCE in the case of combining GA and EA algorithms is 8% higher than when these algorithms are separately adopted.","PeriodicalId":59014,"journal":{"name":"高性能计算技术","volume":"31 1","pages":"82-85"},"PeriodicalIF":0.0,"publicationDate":"2022-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78497338","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 : 2022-03-02DOI: 10.1109/dchpc55044.2022.9732128
A. Yaghoobnia, M. Kazemi
In this paper, a collocation method will introduce. This method is applied to obtain the numerical solution of a class of linear stochastic integral equations. For this purpose, the integrals of these equations are expressed in terms of Legendre polynomials. Then they are applied to the stochastic integral equation and calculate the obtained equations at the node points, where results in a linear system that will solve by conventional methods. Finally, to evaluate the effectiveness of the proposed method, an example is provided, and the numerical results are analyzed.
{"title":"A collocation method for the numerical solution of a class of linear stochastic integral equations based on Legendre polynomials","authors":"A. Yaghoobnia, M. Kazemi","doi":"10.1109/dchpc55044.2022.9732128","DOIUrl":"https://doi.org/10.1109/dchpc55044.2022.9732128","url":null,"abstract":"In this paper, a collocation method will introduce. This method is applied to obtain the numerical solution of a class of linear stochastic integral equations. For this purpose, the integrals of these equations are expressed in terms of Legendre polynomials. Then they are applied to the stochastic integral equation and calculate the obtained equations at the node points, where results in a linear system that will solve by conventional methods. Finally, to evaluate the effectiveness of the proposed method, an example is provided, and the numerical results are analyzed.","PeriodicalId":59014,"journal":{"name":"高性能计算技术","volume":"30 1","pages":"26-30"},"PeriodicalIF":0.0,"publicationDate":"2022-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88357559","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 : 2022-03-02DOI: 10.1109/dchpc55044.2022.9732156
Maral Kolahkaj
Today, due to the development of technology and the advent of web 2.0 applications, different users prefer to do many of their personal tasks over the Internet. Due to the huge amount of information on the web, retrieving the appropriate information for each user has become a challenging task. Content-based image retrieval is one of the most important research fields in digital image processing domain, which searches the similar images to the target image by extracting visual content from the query image. In this regard, many studies have been conducted to increase the accuracy of image retrieval systems. However, due to the explosive growth of storage resources and the lack of a responsible system for image retrieval, it is still considered as one of the most attractive fields of research. In this paper, a method is proposed that extracts the appropriate features using a hybrid method, and then searches the images that are similar to the target image. In this way, self-supervised learning approach is utilized to provide the most similar images. Experimental results based on the Corel dataset show that the accuracy of the proposed method has increased compared to the other methods.
{"title":"An image retrieval approach based on feature extraction and self-supervised learning","authors":"Maral Kolahkaj","doi":"10.1109/dchpc55044.2022.9732156","DOIUrl":"https://doi.org/10.1109/dchpc55044.2022.9732156","url":null,"abstract":"Today, due to the development of technology and the advent of web 2.0 applications, different users prefer to do many of their personal tasks over the Internet. Due to the huge amount of information on the web, retrieving the appropriate information for each user has become a challenging task. Content-based image retrieval is one of the most important research fields in digital image processing domain, which searches the similar images to the target image by extracting visual content from the query image. In this regard, many studies have been conducted to increase the accuracy of image retrieval systems. However, due to the explosive growth of storage resources and the lack of a responsible system for image retrieval, it is still considered as one of the most attractive fields of research. In this paper, a method is proposed that extracts the appropriate features using a hybrid method, and then searches the images that are similar to the target image. In this way, self-supervised learning approach is utilized to provide the most similar images. Experimental results based on the Corel dataset show that the accuracy of the proposed method has increased compared to the other methods.","PeriodicalId":59014,"journal":{"name":"高性能计算技术","volume":"50 1","pages":"46-51"},"PeriodicalIF":0.0,"publicationDate":"2022-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85807664","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 : 2022-03-02DOI: 10.1109/dchpc55044.2022.9732157
Noor Ul Ain, Ali Irfan, N. Iltaf, Mahmood ul Hassan
Quality of Service (QoS) Aware recommender system considers the quality of service to recommend personalized web services to the user. Quality of Service parameters also includes response time and throughput that a user receives when invoking a web service. There exist numerous collaborative filtering techniques that tend to predict Quality of Service value; however, existing techniques only use the client-side information of QoS and neglect the service's contextual attributes. This paper proposes a new Web Service Recommendation System that will consider the contextual attributes of Web services. The proposed method collects the contextual properties from WSDL files to cluster Web services based on their attribute similarities. Thus, more accurate neighbour selection takes place and prediction value is determined using QoS record; in addition to this, a user-influenced prediction value is also determined. To map both, service, and user influence on QoS prediction, a hybrid memory-based CF model is developed. The effectiveness and reliability of the proposed system is verified by the results of experiments.
QoS (Quality of Service)感知式推荐系统考虑服务质量向用户推荐个性化的web服务。服务质量参数还包括用户在调用web服务时接收到的响应时间和吞吐量。存在许多倾向于预测服务质量价值的协同过滤技术;然而，现有的技术只使用QoS的客户端信息，而忽略了服务的上下文属性。本文提出了一种考虑Web服务上下文属性的Web服务推荐系统。提出的方法从WSDL文件收集上下文属性，并根据属性相似性对Web服务进行集群。这样，可以更准确地选择邻居，并利用QoS记录确定预测值;除此之外，还确定了用户影响的预测值。为了映射服务和用户对QoS预测的影响，开发了一种基于内存的混合CF模型。实验结果验证了该系统的有效性和可靠性。
{"title":"A Hybrid Collaborative Filtering Technique for Web Service Recommendation using Contextual Attributes of Web Services","authors":"Noor Ul Ain, Ali Irfan, N. Iltaf, Mahmood ul Hassan","doi":"10.1109/dchpc55044.2022.9732157","DOIUrl":"https://doi.org/10.1109/dchpc55044.2022.9732157","url":null,"abstract":"Quality of Service (QoS) Aware recommender system considers the quality of service to recommend personalized web services to the user. Quality of Service parameters also includes response time and throughput that a user receives when invoking a web service. There exist numerous collaborative filtering techniques that tend to predict Quality of Service value; however, existing techniques only use the client-side information of QoS and neglect the service's contextual attributes. This paper proposes a new Web Service Recommendation System that will consider the contextual attributes of Web services. The proposed method collects the contextual properties from WSDL files to cluster Web services based on their attribute similarities. Thus, more accurate neighbour selection takes place and prediction value is determined using QoS record; in addition to this, a user-influenced prediction value is also determined. To map both, service, and user influence on QoS prediction, a hybrid memory-based CF model is developed. The effectiveness and reliability of the proposed system is verified by the results of experiments.","PeriodicalId":59014,"journal":{"name":"高性能计算技术","volume":"41 1","pages":"60-65"},"PeriodicalIF":0.0,"publicationDate":"2022-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77958544","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 : 2022-03-02DOI: 10.1109/dchpc55044.2022.9732117
Hina Alam, Muhammad Shaharyar Yaqub, Ibrahim Nadir
Internet of Things (IoT) devices is being used in countless network applications. However, due to their insecure nature, the wide adoption of these devices has also increased the possibility of cyber-attacks. There is a need for a robust security mechanism to detect and safeguard against numerous threats. Machine Learning (ML) techniques have been used to detect attacks on different networking layers but training only the network, transport, or link-layer data has proven to be inadequate. Thus, opening paths for attackers to take control and penetrate the networks. Leveraging from this inadequacy, we have employed Machine Learning technology to detect attacks on IoT devices using the application, transport, and network layer data. In particular, we have focused on feature extraction of Application layer data to identify nefariousness in packets. Furthermore, for packet classification, we are also extracting features from the network layer and transport layer. Our simulation results have promised accuracy of 88% and 92% using different ML algorithms. We have also identified possible future work that can be used to validate the solution.
{"title":"Detecting IoT Attacks using Multi-Layer Data Through Machine Learning","authors":"Hina Alam, Muhammad Shaharyar Yaqub, Ibrahim Nadir","doi":"10.1109/dchpc55044.2022.9732117","DOIUrl":"https://doi.org/10.1109/dchpc55044.2022.9732117","url":null,"abstract":"Internet of Things (IoT) devices is being used in countless network applications. However, due to their insecure nature, the wide adoption of these devices has also increased the possibility of cyber-attacks. There is a need for a robust security mechanism to detect and safeguard against numerous threats. Machine Learning (ML) techniques have been used to detect attacks on different networking layers but training only the network, transport, or link-layer data has proven to be inadequate. Thus, opening paths for attackers to take control and penetrate the networks. Leveraging from this inadequacy, we have employed Machine Learning technology to detect attacks on IoT devices using the application, transport, and network layer data. In particular, we have focused on feature extraction of Application layer data to identify nefariousness in packets. Furthermore, for packet classification, we are also extracting features from the network layer and transport layer. Our simulation results have promised accuracy of 88% and 92% using different ML algorithms. We have also identified possible future work that can be used to validate the solution.","PeriodicalId":59014,"journal":{"name":"高性能计算技术","volume":"26 1","pages":"52-59"},"PeriodicalIF":0.0,"publicationDate":"2022-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91101493","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 : 2022-03-02DOI: 10.1109/dchpc55044.2022.9732084
K. Borna, Parsa Mohammadrezaei
In this paper, we propose a new algorithm for mining frequent patterns in image databases. Our method mines patterns with more accuracy than a previously known algorithm and can be beneficial, where small differences in object locations can change the pattern. In this regard, we generate larger patterns from smaller ones and check whether the support for each candidate is less than a user-specified amount.
{"title":"Mining Frequent Spatial Patterns in Image Databases with 17D-SPA Representation","authors":"K. Borna, Parsa Mohammadrezaei","doi":"10.1109/dchpc55044.2022.9732084","DOIUrl":"https://doi.org/10.1109/dchpc55044.2022.9732084","url":null,"abstract":"In this paper, we propose a new algorithm for mining frequent patterns in image databases. Our method mines patterns with more accuracy than a previously known algorithm and can be beneficial, where small differences in object locations can change the pattern. In this regard, we generate larger patterns from smaller ones and check whether the support for each candidate is less than a user-specified amount.","PeriodicalId":59014,"journal":{"name":"高性能计算技术","volume":"37 1","pages":"1-7"},"PeriodicalIF":0.0,"publicationDate":"2022-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86678815","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 : 2022-03-02DOI: 10.1109/dchpc55044.2022.9732149
Abolfazl Rajaiyan, Somayeh Sobati-Moghadam
Smart homes are currently being empowered by Internet of Things (IoT) innovations and applications. IoT-based systems are designed to achieve low power consumption and optimal performance. In many situations, IoT devices are powered by batteries, and power efficiency is the most crucial need for them to operate reliably for long periods of time. Low power consumption and increasing system lifetime are two important problems of IoT. This paper describes a formula for designing IoT systems depending on the available power of the resource. This paper presents an effective technique to reduce power consumption. The proposed method is based on the available power in the resources of an IoT system. First, the power consumption is calculated to meet the system's requirements, and then the system is developed appropriately. Furthermore, by constructing a smart home system, the quantity of power storage in a specific situation is investigated, and a formula for designing IoT systems based on the available power has been presented.
{"title":"Optimized Power Consumption Formula for Designing IoT-Based Systems","authors":"Abolfazl Rajaiyan, Somayeh Sobati-Moghadam","doi":"10.1109/dchpc55044.2022.9732149","DOIUrl":"https://doi.org/10.1109/dchpc55044.2022.9732149","url":null,"abstract":"Smart homes are currently being empowered by Internet of Things (IoT) innovations and applications. IoT-based systems are designed to achieve low power consumption and optimal performance. In many situations, IoT devices are powered by batteries, and power efficiency is the most crucial need for them to operate reliably for long periods of time. Low power consumption and increasing system lifetime are two important problems of IoT. This paper describes a formula for designing IoT systems depending on the available power of the resource. This paper presents an effective technique to reduce power consumption. The proposed method is based on the available power in the resources of an IoT system. First, the power consumption is calculated to meet the system's requirements, and then the system is developed appropriately. Furthermore, by constructing a smart home system, the quantity of power storage in a specific situation is investigated, and a formula for designing IoT systems based on the available power has been presented.","PeriodicalId":59014,"journal":{"name":"高性能计算技术","volume":"22 1","pages":"74-77"},"PeriodicalIF":0.0,"publicationDate":"2022-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89435887","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 : 2021-01-28DOI: 10.1007/978-3-030-60265-9_8
L. Priya, A. Sathya, S. ThangaRevathi
{"title":"Deep Learning in Healthcare","authors":"L. Priya, A. Sathya, S. ThangaRevathi","doi":"10.1007/978-3-030-60265-9_8","DOIUrl":"https://doi.org/10.1007/978-3-030-60265-9_8","url":null,"abstract":"","PeriodicalId":59014,"journal":{"name":"高性能计算技术","volume":"227 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80166207","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：