Pub Date : 2017-11-01DOI: 10.1109/ICSESS.2017.8343021
Idris Khan, Honglu Zhu, Jianxi Yao, Danish Khan
Solar energy has the property of alternating, fluctuation and periodicity, and it has severe impact on large scale photovoltaic (PV) grid-connected generation. This turn power utilities contrary to use PV power since the forecasting and overall assessment of the grid becomes very difficult. To develop a reliable algorithm that can minimize the errors associated with forecasting the nearby future PV power generation is particularly helpful for efficiently integration into the grid. PV power prediction can play a significant role in undertaking these challenges. This paper presents 3 days ahead power output forecasting of a PV system using a Theoretical Solar radiation and Elman Neural Network (ENN) software engineering technique by including the relations of PV power with solar radiation, temperature, humidity, and wind speed data. In the proposed method, the ENN is applied to have a significant effect on random PV power time-series data, and tackle the nonlinear fluctuations in a better approach.
{"title":"Photovoltaic power forecasting based on Elman Neural Network software engineering method","authors":"Idris Khan, Honglu Zhu, Jianxi Yao, Danish Khan","doi":"10.1109/ICSESS.2017.8343021","DOIUrl":"https://doi.org/10.1109/ICSESS.2017.8343021","url":null,"abstract":"Solar energy has the property of alternating, fluctuation and periodicity, and it has severe impact on large scale photovoltaic (PV) grid-connected generation. This turn power utilities contrary to use PV power since the forecasting and overall assessment of the grid becomes very difficult. To develop a reliable algorithm that can minimize the errors associated with forecasting the nearby future PV power generation is particularly helpful for efficiently integration into the grid. PV power prediction can play a significant role in undertaking these challenges. This paper presents 3 days ahead power output forecasting of a PV system using a Theoretical Solar radiation and Elman Neural Network (ENN) software engineering technique by including the relations of PV power with solar radiation, temperature, humidity, and wind speed data. In the proposed method, the ENN is applied to have a significant effect on random PV power time-series data, and tackle the nonlinear fluctuations in a better approach.","PeriodicalId":179815,"journal":{"name":"2017 8th IEEE International Conference on Software Engineering and Service Science (ICSESS)","volume":"254 23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115200177","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 : 2017-11-01DOI: 10.1109/ICSESS.2017.8343051
Chuanqi Wang, Yanhui Li
There are a number of indexes proposed in many studies to evaluate the quality of journals. Among them, H-index is a recently proposed index as a useful supplement to journal impact factor. However, current H-index is based on long journal history. Immediate changes of citations of journals are often ignored by H-index. In this paper, we propose 5-year H-index to solve this problem. 5-year H-index evaluates the immediate citation performance (in this year) of a journal's papers published in the last 5 years. We can measure journals by the recent citations with 5-year H-index, which can be a new way to determine the value of journals.
在许多研究中提出了许多评价期刊质量的指标。其中，h指数是最近提出的对期刊影响因子进行有益补充的指标。然而，目前的h指数是基于长期的期刊历史。期刊被引用的即时变化常常被h指数忽略。本文提出了5年h指数来解决这一问题。5年h指数(5- 5 h index)是对期刊近5年发表的论文在本年度的直接被引表现进行评价。利用最近5年的被引次数和h指数来衡量期刊的价值，为期刊价值的确定提供了一种新的途径。
{"title":"Applying H-index within 5-year citations window","authors":"Chuanqi Wang, Yanhui Li","doi":"10.1109/ICSESS.2017.8343051","DOIUrl":"https://doi.org/10.1109/ICSESS.2017.8343051","url":null,"abstract":"There are a number of indexes proposed in many studies to evaluate the quality of journals. Among them, H-index is a recently proposed index as a useful supplement to journal impact factor. However, current H-index is based on long journal history. Immediate changes of citations of journals are often ignored by H-index. In this paper, we propose 5-year H-index to solve this problem. 5-year H-index evaluates the immediate citation performance (in this year) of a journal's papers published in the last 5 years. We can measure journals by the recent citations with 5-year H-index, which can be a new way to determine the value of journals.","PeriodicalId":179815,"journal":{"name":"2017 8th IEEE International Conference on Software Engineering and Service Science (ICSESS)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114672746","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 : 2017-11-01DOI: 10.1109/ICSESS.2017.8342969
Jiewen Wan, Qingshan Li, Lu Wang, Liu He, Yvjie Li
Software Self-adaption (SA) is a promising technology to reduce the cost of software maintenance. However, the complexities of software changes such as various and producing different effects, interrelated and occurring in an unpredictable context challenge the SA. The current methods may be insufficient to provide the required self-adaptation abilities to handle all the existent complexities of changes. Thus, this paper presents a self-adaptation framework which can provide a multi-agent system for self-adaptation control to equip software system with the required adaptation abilities. we employ the hybrid control mode and construct a two-layer MAPE control structure to deal with changes hierarchically. Multi-Objective Evolutionary Algorithm and Reinforcement Learning are applied to plan an adequate strategy for these changes. Finally, in order to validate the framework, we exemplify these ideas with a meta-Search system and confirm the required self-adaptive ability.
{"title":"A self-adaptation framework for dealing with the complexities of software changes","authors":"Jiewen Wan, Qingshan Li, Lu Wang, Liu He, Yvjie Li","doi":"10.1109/ICSESS.2017.8342969","DOIUrl":"https://doi.org/10.1109/ICSESS.2017.8342969","url":null,"abstract":"Software Self-adaption (SA) is a promising technology to reduce the cost of software maintenance. However, the complexities of software changes such as various and producing different effects, interrelated and occurring in an unpredictable context challenge the SA. The current methods may be insufficient to provide the required self-adaptation abilities to handle all the existent complexities of changes. Thus, this paper presents a self-adaptation framework which can provide a multi-agent system for self-adaptation control to equip software system with the required adaptation abilities. we employ the hybrid control mode and construct a two-layer MAPE control structure to deal with changes hierarchically. Multi-Objective Evolutionary Algorithm and Reinforcement Learning are applied to plan an adequate strategy for these changes. Finally, in order to validate the framework, we exemplify these ideas with a meta-Search system and confirm the required self-adaptive ability.","PeriodicalId":179815,"journal":{"name":"2017 8th IEEE International Conference on Software Engineering and Service Science (ICSESS)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122476971","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 : 2017-11-01DOI: 10.1109/ICSESS.2017.8343003
Qiang Li, Hui Li, Zhongling Wen, Pengfei Yuan
Kad is the most popular P2P file sharing system. Previous works only focus on the global peers' collection or monitoring the lookup traffic. Based on our online measurement, we find that each benign peer's routing table only has 400–600 peers. We further study the Kad's source codes and track the routing table's change process. And finally, we explain that the unique Kad routing table's structure and the total online peer number lead to this result. We also do the large-scale experiment to prove our conclusion.
{"title":"Why Kad's routing table has hundreds of peers","authors":"Qiang Li, Hui Li, Zhongling Wen, Pengfei Yuan","doi":"10.1109/ICSESS.2017.8343003","DOIUrl":"https://doi.org/10.1109/ICSESS.2017.8343003","url":null,"abstract":"Kad is the most popular P2P file sharing system. Previous works only focus on the global peers' collection or monitoring the lookup traffic. Based on our online measurement, we find that each benign peer's routing table only has 400–600 peers. We further study the Kad's source codes and track the routing table's change process. And finally, we explain that the unique Kad routing table's structure and the total online peer number lead to this result. We also do the large-scale experiment to prove our conclusion.","PeriodicalId":179815,"journal":{"name":"2017 8th IEEE International Conference on Software Engineering and Service Science (ICSESS)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121789239","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 : 2017-11-01DOI: 10.1109/ICSESS.2017.8343058
Somesh Katta, M. Babu
Convolutional Neural Network (CNN) is a Multi-Layer Perceptron Neural Network (MLP), specially designed for classification and identification of image data. MLPs are very useful but very slow for learning image features. Even for small images MLPs takes a lot of time to learn the features. On contrary, Convnets detects the features locally and propagate them to the neighboring layer so that the learning process is easier and efficient. Image reduction is a process normally used to reduce the number of learning parameters. The present paper is aimed at designing a new technique to convolve the input image, using Deep CNN algorithm and then reduce the image dimension by pooling techniques. The new technique is applied for image classification of flue-cured tobacco leaves. About 120 samples of cured tobacco leaves are taken for training the CNN and reduced the image dimensions from 1450×1680 to 256×256 RGB. Here four hidden layer CNN is considered and performed convolution and pooling on input images with sixteen, thirty two and sixty four feature kernels on first three hidden layers and fourth layer is connected to output layer. Max pooling technique is used in the model and classified them into three major classes' class-1, class-2 and class-3 with a global efficiency of 85.10% on the test set consisting about fifteen images of each group. Results from the proposed model are compared with other existing models and shown that the model performs better even with small training set.
{"title":"An approach to classify flue-cured tobacco leaves using deep convolutional neural networks","authors":"Somesh Katta, M. Babu","doi":"10.1109/ICSESS.2017.8343058","DOIUrl":"https://doi.org/10.1109/ICSESS.2017.8343058","url":null,"abstract":"Convolutional Neural Network (CNN) is a Multi-Layer Perceptron Neural Network (MLP), specially designed for classification and identification of image data. MLPs are very useful but very slow for learning image features. Even for small images MLPs takes a lot of time to learn the features. On contrary, Convnets detects the features locally and propagate them to the neighboring layer so that the learning process is easier and efficient. Image reduction is a process normally used to reduce the number of learning parameters. The present paper is aimed at designing a new technique to convolve the input image, using Deep CNN algorithm and then reduce the image dimension by pooling techniques. The new technique is applied for image classification of flue-cured tobacco leaves. About 120 samples of cured tobacco leaves are taken for training the CNN and reduced the image dimensions from 1450×1680 to 256×256 RGB. Here four hidden layer CNN is considered and performed convolution and pooling on input images with sixteen, thirty two and sixty four feature kernels on first three hidden layers and fourth layer is connected to output layer. Max pooling technique is used in the model and classified them into three major classes' class-1, class-2 and class-3 with a global efficiency of 85.10% on the test set consisting about fifteen images of each group. Results from the proposed model are compared with other existing models and shown that the model performs better even with small training set.","PeriodicalId":179815,"journal":{"name":"2017 8th IEEE International Conference on Software Engineering and Service Science (ICSESS)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125043767","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 : 2017-11-01DOI: 10.1109/ICSESS.2017.8343011
Wei Hu, Bo Wang
We propose a novel method for template matching in unconstrained environments. The essence of it is the Multiple Information Matching (MSCE) which combines SSDA, CLD, EHD, a variety of algorithms, a useful, robust and parameter-free similarity measure between two sets of points. Since the SSDA algorithm was easy to influence the image noise and illumination, CLD and EHD are added to make the matching more accurate. Experimental results show that MSCE algorithm is more accurate in matching position.
{"title":"A template matching algorithm for high precision positioning","authors":"Wei Hu, Bo Wang","doi":"10.1109/ICSESS.2017.8343011","DOIUrl":"https://doi.org/10.1109/ICSESS.2017.8343011","url":null,"abstract":"We propose a novel method for template matching in unconstrained environments. The essence of it is the Multiple Information Matching (MSCE) which combines SSDA, CLD, EHD, a variety of algorithms, a useful, robust and parameter-free similarity measure between two sets of points. Since the SSDA algorithm was easy to influence the image noise and illumination, CLD and EHD are added to make the matching more accurate. Experimental results show that MSCE algorithm is more accurate in matching position.","PeriodicalId":179815,"journal":{"name":"2017 8th IEEE International Conference on Software Engineering and Service Science (ICSESS)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123602564","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 : 2017-11-01DOI: 10.1109/ICSESS.2017.8342902
Hongjuan Yang, Kaifan Ji, Yunfei Yang, W. Duan, H. Deng, Bo Liang
The traditional mask method and background fitting method can not correct effectively the solar image with uneven illumination. We adopt a correct method based on Retinex for the solar image with uneven illumination. The quality of image is improved by compressing the range of brightness and increasing the contrast by separately processing the effect of illumination and reflectivity to the intensity value. It could reveal the detailed character of the shadow area of the image. By contrasting four evaluate indexes, including the mean intensity, the image entropy, the image contrast and the peak signal to noise ratio (PSNR), this method is proved to be effective in the solar image with uneven illumination.
{"title":"A correct method based on retinex for the solar image with uneven illumination","authors":"Hongjuan Yang, Kaifan Ji, Yunfei Yang, W. Duan, H. Deng, Bo Liang","doi":"10.1109/ICSESS.2017.8342902","DOIUrl":"https://doi.org/10.1109/ICSESS.2017.8342902","url":null,"abstract":"The traditional mask method and background fitting method can not correct effectively the solar image with uneven illumination. We adopt a correct method based on Retinex for the solar image with uneven illumination. The quality of image is improved by compressing the range of brightness and increasing the contrast by separately processing the effect of illumination and reflectivity to the intensity value. It could reveal the detailed character of the shadow area of the image. By contrasting four evaluate indexes, including the mean intensity, the image entropy, the image contrast and the peak signal to noise ratio (PSNR), this method is proved to be effective in the solar image with uneven illumination.","PeriodicalId":179815,"journal":{"name":"2017 8th IEEE International Conference on Software Engineering and Service Science (ICSESS)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115020901","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 : 2017-11-01DOI: 10.1109/ICSESS.2017.8342851
Jack H. C. Wu, J. Keung
Analogy-based software effort estimation is one of the most popular estimation methods. It is built upon the principle of case-based reasoning (CBR) based on the k-th similar projects completed in the past. Therefore the determination of the k value is crucial to the prediction performance. Various research have been carried out to use a single and fixed k value for experiments, and it is known that dynamically allocated k values in an experiment will produce the optimized performance. This paper proposes an interesting technique based on hierarchical clustering to produce a range for k through various cluster quality criteria. We find that complete linkage clustering is more suitable for large datasets while single linkage clustering is suitable for small datasets. The method searches for optimized k values based on the proposed heuristic optimization technique, which have the advantages of easy computation and optimized for the dataset being investigated. Datasets from the PROMISE repository have been used to evaluate the proposed technique. The results of the experiments show that the proposed method is able to determine an optimized set of k values for analogy-based prediction, and to give estimates that outperformed traditional models based on a fixed k value. The implication is significant in that the analogy-based model will be optimized according the dataset being used, without the need to ask an expert to determining a single, fixed k value.
{"title":"Utilizing cluster quality in hierarchical clustering for analogy-based software effort estimation","authors":"Jack H. C. Wu, J. Keung","doi":"10.1109/ICSESS.2017.8342851","DOIUrl":"https://doi.org/10.1109/ICSESS.2017.8342851","url":null,"abstract":"Analogy-based software effort estimation is one of the most popular estimation methods. It is built upon the principle of case-based reasoning (CBR) based on the k-th similar projects completed in the past. Therefore the determination of the k value is crucial to the prediction performance. Various research have been carried out to use a single and fixed k value for experiments, and it is known that dynamically allocated k values in an experiment will produce the optimized performance. This paper proposes an interesting technique based on hierarchical clustering to produce a range for k through various cluster quality criteria. We find that complete linkage clustering is more suitable for large datasets while single linkage clustering is suitable for small datasets. The method searches for optimized k values based on the proposed heuristic optimization technique, which have the advantages of easy computation and optimized for the dataset being investigated. Datasets from the PROMISE repository have been used to evaluate the proposed technique. The results of the experiments show that the proposed method is able to determine an optimized set of k values for analogy-based prediction, and to give estimates that outperformed traditional models based on a fixed k value. The implication is significant in that the analogy-based model will be optimized according the dataset being used, without the need to ask an expert to determining a single, fixed k value.","PeriodicalId":179815,"journal":{"name":"2017 8th IEEE International Conference on Software Engineering and Service Science (ICSESS)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130719829","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 : 2017-11-01DOI: 10.1109/ICSESS.2017.8342973
Pang Jiazhen, Li Na, Hou Xiaohui
It is of great significance to reduce the cost and improve the product quality by using virtual verification platform to evaluate the performance of aircraft maintenance process. A virtual maintenance process modeling method is proposed for the qualitative and quantitative evaluation of ergonomics in virtual environment. Firstly, the definition of virtual maintenance scene is given, and the essential elements of virtual environment analysis are defined. Then, considering the needs of process validation and simulation analysis which are two aspects of the maintenance work, sets up “maintenance tasks — typical operation — typical action” three-layer work element decomposition model, and gives the definition of information and organization methods of various elements. Secondly, the performance evaluation process of virtual maintenance based on typical work elements is established. Finally, the effectiveness of the proposed method is verified by an example of aircraft landing gear tire maintenance.
{"title":"The virtual maintenance process modeling method for performance assessment","authors":"Pang Jiazhen, Li Na, Hou Xiaohui","doi":"10.1109/ICSESS.2017.8342973","DOIUrl":"https://doi.org/10.1109/ICSESS.2017.8342973","url":null,"abstract":"It is of great significance to reduce the cost and improve the product quality by using virtual verification platform to evaluate the performance of aircraft maintenance process. A virtual maintenance process modeling method is proposed for the qualitative and quantitative evaluation of ergonomics in virtual environment. Firstly, the definition of virtual maintenance scene is given, and the essential elements of virtual environment analysis are defined. Then, considering the needs of process validation and simulation analysis which are two aspects of the maintenance work, sets up “maintenance tasks — typical operation — typical action” three-layer work element decomposition model, and gives the definition of information and organization methods of various elements. Secondly, the performance evaluation process of virtual maintenance based on typical work elements is established. Finally, the effectiveness of the proposed method is verified by an example of aircraft landing gear tire maintenance.","PeriodicalId":179815,"journal":{"name":"2017 8th IEEE International Conference on Software Engineering and Service Science (ICSESS)","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133897599","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 : 2017-11-01DOI: 10.1109/ICSESS.2017.8342943
Zihan Ren, Shuangyuan Yang, F. Zou, Fan Yang, Chaoyang Luan, Kai Li
This paper presents a method for real-time detection and tracking of the human face. The proposed method combines the Convolution Neural Network detection and the Kalman Filter tracking. Convolution Neural Network is used to detect face in video, which is more accurate than traditional detection method. When the face is largely deflected or severely occluded, Kalman Filter tracking is utilized to predict the face position. The objective is to increase the face detection rate, while meet the real time requirements. Our method is implemented based on Caffe framework. The experimental results show that our method achieves superior accuracy over the existing techniques and keeps real time performance.
{"title":"A face tracking framework based on convolutional neural networks and Kalman filter","authors":"Zihan Ren, Shuangyuan Yang, F. Zou, Fan Yang, Chaoyang Luan, Kai Li","doi":"10.1109/ICSESS.2017.8342943","DOIUrl":"https://doi.org/10.1109/ICSESS.2017.8342943","url":null,"abstract":"This paper presents a method for real-time detection and tracking of the human face. The proposed method combines the Convolution Neural Network detection and the Kalman Filter tracking. Convolution Neural Network is used to detect face in video, which is more accurate than traditional detection method. When the face is largely deflected or severely occluded, Kalman Filter tracking is utilized to predict the face position. The objective is to increase the face detection rate, while meet the real time requirements. Our method is implemented based on Caffe framework. The experimental results show that our method achieves superior accuracy over the existing techniques and keeps real time performance.","PeriodicalId":179815,"journal":{"name":"2017 8th IEEE International Conference on Software Engineering and Service Science (ICSESS)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134112848","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：