Pub Date : 2018-05-01DOI: 10.1109/ICESIT-ICICTES.2018.8442068
Duangkamol Tedlek, S. Khoomboon, T. Kasetkasem, T. Chanwimaluang, I. Kumazawa
This paper proposes a cloud removal algorithm for satellite images that are obscured by clouds. Our concept is to separate the land cover map into the segments. After that, we localize and indicate the degree of cloud thickness map by using a level set function. As the continuity of the level set function, the gradient approach is deployed by using the calculus of variation. Our example shows that our model can mitigate the effect clouds in images.
{"title":"A Cloud-Contamination Removal Algorithm by Combining Image Segmentation and Level-set-based Approaches for Remote Sensing Images","authors":"Duangkamol Tedlek, S. Khoomboon, T. Kasetkasem, T. Chanwimaluang, I. Kumazawa","doi":"10.1109/ICESIT-ICICTES.2018.8442068","DOIUrl":"https://doi.org/10.1109/ICESIT-ICICTES.2018.8442068","url":null,"abstract":"This paper proposes a cloud removal algorithm for satellite images that are obscured by clouds. Our concept is to separate the land cover map into the segments. After that, we localize and indicate the degree of cloud thickness map by using a level set function. As the continuity of the level set function, the gradient approach is deployed by using the calculus of variation. Our example shows that our model can mitigate the effect clouds in images.","PeriodicalId":57136,"journal":{"name":"单片机与嵌入式系统应用","volume":"107 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90765485","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 : 2018-05-01DOI: 10.1109/ICESIT-ICICTES.2018.8442069
C. Jeenanunta, Rujira Chaysiri, L. Thong
In this paper, we investigate the prediction of daily stock prices of the top five companies in the Thai SET50 index. A Recurrent Neural Network (RNN) with Long Short-Term Memory (LSTM) is applied to forecast the next daily stock price (High, Low, Open, Close). Deep Belief Network (DBN) is applied to compare the result with LSTM. The test data are CPALL, SCB, SCC, KBANK, and PTT from the SET50 index. The purpose of selecting these five stocks is to compare how the model performs in different stocks with various volatility. There are two experiments of five stocks from the SET50 index. The first experiment compared the MAPE with different length of training data. The experiment is conducted by using training data for one, three, and five-year. PTT and SCC stock give the lowest median value of MAPE error for five-year training data. KBANK, SCB, and CPALL stock give the lowest median value of MAPE error for one-year training data. In the second experiment, the number of looks back and input are varied. The result with one look back and four inputs gives the best performance for stock price prediction. By comparing different technique, the result show that LSTM give the best performance with CPALL, SCB, and KTB with less than 2% error. DBN give the best performance with PTT and SCC with less than 2% error.
{"title":"Stock Price Prediction With Long Short-Term Memory Recurrent Neural Network","authors":"C. Jeenanunta, Rujira Chaysiri, L. Thong","doi":"10.1109/ICESIT-ICICTES.2018.8442069","DOIUrl":"https://doi.org/10.1109/ICESIT-ICICTES.2018.8442069","url":null,"abstract":"In this paper, we investigate the prediction of daily stock prices of the top five companies in the Thai SET50 index. A Recurrent Neural Network (RNN) with Long Short-Term Memory (LSTM) is applied to forecast the next daily stock price (High, Low, Open, Close). Deep Belief Network (DBN) is applied to compare the result with LSTM. The test data are CPALL, SCB, SCC, KBANK, and PTT from the SET50 index. The purpose of selecting these five stocks is to compare how the model performs in different stocks with various volatility. There are two experiments of five stocks from the SET50 index. The first experiment compared the MAPE with different length of training data. The experiment is conducted by using training data for one, three, and five-year. PTT and SCC stock give the lowest median value of MAPE error for five-year training data. KBANK, SCB, and CPALL stock give the lowest median value of MAPE error for one-year training data. In the second experiment, the number of looks back and input are varied. The result with one look back and four inputs gives the best performance for stock price prediction. By comparing different technique, the result show that LSTM give the best performance with CPALL, SCB, and KTB with less than 2% error. DBN give the best performance with PTT and SCC with less than 2% error.","PeriodicalId":57136,"journal":{"name":"单片机与嵌入式系统应用","volume":"38 1","pages":"1-7"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86818105","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 : 2018-05-01DOI: 10.1109/ICESIT-ICICTES.2018.8442073
U. Tuntoolavest, Chayanon Athanan, Koravit Panwong
This paper proposes a new decoding technique called “MP-VSD” for LDPC codes with large nonbinary symbols. It combines Hard Decision Message Passing (HDMP) with Vector Symbol Decoding (VSD). VSD usually uses very short block codes to limit the number of error symbols, which limits the size of matrix inversion required in the VSD decoding step. MP-VSD can correct more than 60% of the correctable error patterns of VSD for an (60, 30) LDPC code with no matrix inversions in a 2-state fading channel model. Thus, longer block codes may be used for nonbinary symbols.
{"title":"Message Passing-Vector Symbol Decoding for LDPC Codes with Nonbinary Symbols","authors":"U. Tuntoolavest, Chayanon Athanan, Koravit Panwong","doi":"10.1109/ICESIT-ICICTES.2018.8442073","DOIUrl":"https://doi.org/10.1109/ICESIT-ICICTES.2018.8442073","url":null,"abstract":"This paper proposes a new decoding technique called “MP-VSD” for LDPC codes with large nonbinary symbols. It combines Hard Decision Message Passing (HDMP) with Vector Symbol Decoding (VSD). VSD usually uses very short block codes to limit the number of error symbols, which limits the size of matrix inversion required in the VSD decoding step. MP-VSD can correct more than 60% of the correctable error patterns of VSD for an (60, 30) LDPC code with no matrix inversions in a 2-state fading channel model. Thus, longer block codes may be used for nonbinary symbols.","PeriodicalId":57136,"journal":{"name":"单片机与嵌入式系统应用","volume":"52 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90667019","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 : 2018-05-01DOI: 10.1109/ICESIT-ICICTES.2018.8442067
S. Poomsombut, C. Limsakul, P. Phukpattaranont
In order to determine the linear relation between the features of EMG signals and biting force, the correlation coefficient (r) is used to select the appropriate features of EMG signal providing the high linear relationship. The experimental results showed that when segmentation of EMG signals for feature calculation by assigning window sizes equal to window increment, the correlation coefficient is greater than that the window sizes are larger window increment. Feature extracted from the EMG signal with a 500 ms window size and a 500 ms window increment in time domain provides the best linear relationship with the biting force levels. Moreover, the feature providing the best correlation is Willison Amplitude (WAMP) with r = 0.75. On the other hand, the results obtained from other features are quite similar (0.75 >r>0.62).
{"title":"Appropriate Features to Determine Correlation in EMG Signals and Biting Force in Occlusion System","authors":"S. Poomsombut, C. Limsakul, P. Phukpattaranont","doi":"10.1109/ICESIT-ICICTES.2018.8442067","DOIUrl":"https://doi.org/10.1109/ICESIT-ICICTES.2018.8442067","url":null,"abstract":"In order to determine the linear relation between the features of EMG signals and biting force, the correlation coefficient (r) is used to select the appropriate features of EMG signal providing the high linear relationship. The experimental results showed that when segmentation of EMG signals for feature calculation by assigning window sizes equal to window increment, the correlation coefficient is greater than that the window sizes are larger window increment. Feature extracted from the EMG signal with a 500 ms window size and a 500 ms window increment in time domain provides the best linear relationship with the biting force levels. Moreover, the feature providing the best correlation is Willison Amplitude (WAMP) with r = 0.75. On the other hand, the results obtained from other features are quite similar (0.75 >r>0.62).","PeriodicalId":57136,"journal":{"name":"单片机与嵌入式系统应用","volume":"11 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72986352","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 : 2018-05-01DOI: 10.1109/ICESIT-ICICTES.2018.8442062
Wasu Wasusatein, Sukhumpat Nittayawan, W. Kongprawechnon
Induction motor has been an important machine in many applications especially in Electric Vehicles(EVs), The improve in performance of the induction motor will result in a more stable and efficient drive system of the EV which will be beneficial for future applications which was achieved through the introduction of Variable-Speed Drive system. However, in this non ideal world, uncertainty must be considered. Load of induction motor has high uncertainty which cause a high degree of instability or degradation in performance of the system. In order to keep induction motor in control to uncertainty of load, a suitable controller should be introduced to solve the problem. Neural Network Controllers are used widely in non-linear system due to its adaptivity to new conditions as the controller uses a learning system from past inputs and outputs. This study is to apply neural network in auto-tuning PID controller for improving the accuracy of induction motor drive in electrical vehicles when load is uncertain. The final objective is to improve, through the addition of neural network, the robustness and performance of the induction motor.
{"title":"Speed Control Under Load Uncertainty of Induction Motor Using Neural Network Auto-Tuning PID Controller","authors":"Wasu Wasusatein, Sukhumpat Nittayawan, W. Kongprawechnon","doi":"10.1109/ICESIT-ICICTES.2018.8442062","DOIUrl":"https://doi.org/10.1109/ICESIT-ICICTES.2018.8442062","url":null,"abstract":"Induction motor has been an important machine in many applications especially in Electric Vehicles(EVs), The improve in performance of the induction motor will result in a more stable and efficient drive system of the EV which will be beneficial for future applications which was achieved through the introduction of Variable-Speed Drive system. However, in this non ideal world, uncertainty must be considered. Load of induction motor has high uncertainty which cause a high degree of instability or degradation in performance of the system. In order to keep induction motor in control to uncertainty of load, a suitable controller should be introduced to solve the problem. Neural Network Controllers are used widely in non-linear system due to its adaptivity to new conditions as the controller uses a learning system from past inputs and outputs. This study is to apply neural network in auto-tuning PID controller for improving the accuracy of induction motor drive in electrical vehicles when load is uncertain. The final objective is to improve, through the addition of neural network, the robustness and performance of the induction motor.","PeriodicalId":57136,"journal":{"name":"单片机与嵌入式系统应用","volume":"98 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81033241","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 : 2018-05-01DOI: 10.1109/ICESIT-ICICTES.2018.8442057
Wiwat Keyoonwong, W. Khan-ngern, Paritpong Tavichaiyut Viritpol Ruxsri, Vishnu Raksasataya
This paper proposes to record the result of energy consumption and light transmission rate when using PDLC film with green insulated glass, at size lxl sq.m. with 6-12-6 mm. standard thickness. The result of energy consumption and performance in protecting from the sun light are explained. The PDLC energy consumption characteristic and its principle are described. The methodology to test the performance of PDLC film with green insulated glass also incuded. The result indicated that different voltage source level will also be able to affect the light transmission rate. From experiment found that at level 0 volt had a light transmission rate at 22.3 percent, level 15 volts at 28.8 percent, level 30 volts at 32.0 percent, level 45 volts at 33.2 percent, level 55 volts at 33.4 percent and level 70 at 34.0 percent, respectively. All of these values were compared with direct light intensity from outside. In the future, it can be used in purpose for energy saving inside building.
{"title":"PDLC film's energy consumption and performance for light filtration system","authors":"Wiwat Keyoonwong, W. Khan-ngern, Paritpong Tavichaiyut Viritpol Ruxsri, Vishnu Raksasataya","doi":"10.1109/ICESIT-ICICTES.2018.8442057","DOIUrl":"https://doi.org/10.1109/ICESIT-ICICTES.2018.8442057","url":null,"abstract":"This paper proposes to record the result of energy consumption and light transmission rate when using PDLC film with green insulated glass, at size lxl sq.m. with 6-12-6 mm. standard thickness. The result of energy consumption and performance in protecting from the sun light are explained. The PDLC energy consumption characteristic and its principle are described. The methodology to test the performance of PDLC film with green insulated glass also incuded. The result indicated that different voltage source level will also be able to affect the light transmission rate. From experiment found that at level 0 volt had a light transmission rate at 22.3 percent, level 15 volts at 28.8 percent, level 30 volts at 32.0 percent, level 45 volts at 33.2 percent, level 55 volts at 33.4 percent and level 70 at 34.0 percent, respectively. All of these values were compared with direct light intensity from outside. In the future, it can be used in purpose for energy saving inside building.","PeriodicalId":57136,"journal":{"name":"单片机与嵌入式系统应用","volume":"36 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88355402","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 : 2018-05-01DOI: 10.1109/ICESIT-ICICTES.2018.8442059
Paradorn Pimporn, S. Kittipiyakul, J. Kudtongngam, H. Fujita
This paper proposes a method to retrieve the missing data of power consumption of multi-unit air conditioners by using Artificial Neural Networks (ANN). The problem of missing data may occur from a sensor, a microcontroller or a communication problem. We have to retrieve the missing data in order that we can use them to find a solution to improve the efficiency of energy usage in a building. The proposed method uses related data with the missing data i.e. behavior of other air conditioners, a different temperature among inside, outside, and air conditioner pad controls setting value to feed the ANN model. Effectiveness of the proposed method is evaluated by comparison with other state of art classification algorithms.
{"title":"Missing Value Estimation of Energy Consumption of Multi-Unit Air Conditioners using Artificial Neural Networks","authors":"Paradorn Pimporn, S. Kittipiyakul, J. Kudtongngam, H. Fujita","doi":"10.1109/ICESIT-ICICTES.2018.8442059","DOIUrl":"https://doi.org/10.1109/ICESIT-ICICTES.2018.8442059","url":null,"abstract":"This paper proposes a method to retrieve the missing data of power consumption of multi-unit air conditioners by using Artificial Neural Networks (ANN). The problem of missing data may occur from a sensor, a microcontroller or a communication problem. We have to retrieve the missing data in order that we can use them to find a solution to improve the efficiency of energy usage in a building. The proposed method uses related data with the missing data i.e. behavior of other air conditioners, a different temperature among inside, outside, and air conditioner pad controls setting value to feed the ANN model. Effectiveness of the proposed method is evaluated by comparison with other state of art classification algorithms.","PeriodicalId":57136,"journal":{"name":"单片机与嵌入式系统应用","volume":"44 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86079725","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 : 2018-05-01DOI: 10.1109/ICESIT-ICICTES.2018.8442050
K. Sukvichai, Pearpeerune Uthaisang, Patchareeporn Chuengsutthiwong, Pruttapon Maolanon
A talking pen is the evolutional way of learning especially for children because it is fun and interactive. Commercial talking pen use a small infrared camera to capture the hidden dot patterns that hidden around a book's page. Specific sounds are generated according to the location of the pen on the pages. This image processing for recognition technique is complex and need calculation power because it had to calculate relative location and orientation of dots in a group. Although, the talking pen is successful product but it is not flexible to add new pattern or uses different set of patterns. In this research, the new approach for hidden dot pattern recognition is proposed. Convolutional neural networks or CNNs is selected as the recognition software. The system is built on Raspberry Pi Zero W hardware with Raspbian operating system and TensorFlow platform. MobileNet is used in the research since it small and effective for limited resources platform. MobileNet is trained by using the infrared images that captured by infrared camera module that connected to Raspberry Pi. Result shows that the accuracy of the proposed method is good enough and the response is fast enough to be implemented into the real-time commercial product and has ability to expand to any other kind of patterns without limit because the learned network can be updated easily without alter recognition software.
会说话的笔是一种进化的学习方式，尤其是对孩子来说，因为它很有趣，而且是互动的。商业有声笔使用一个小型红外摄像机来捕捉隐藏在书页周围的隐藏点图案。根据笔在页面上的位置产生特定的声音。这种识别技术的图像处理复杂，需要计算一组点的相对位置和方向，需要计算能力。虽然说话笔是成功的产品，但它不能灵活地添加新的图案或使用不同的图案集。本研究提出了一种新的隐点模式识别方法。选择卷积神经网络(cnn)作为识别软件。该系统基于Raspberry Pi Zero W硬件，采用Raspbian操作系统和TensorFlow平台。由于MobileNet在资源有限的平台上体积小、效果好，所以在研究中使用了MobileNet。MobileNet通过使用连接到树莓派的红外相机模块捕获的红外图像进行训练。结果表明，该方法具有较好的准确率和较快的响应速度，可以应用到实时商业产品中，并且由于学习到的网络可以在不改变识别软件的情况下轻松更新，因此可以无限制地扩展到任何其他类型的模式。
{"title":"Hidden Dot Patterns Recognition using CNNs on Raspberry Pi Zero W","authors":"K. Sukvichai, Pearpeerune Uthaisang, Patchareeporn Chuengsutthiwong, Pruttapon Maolanon","doi":"10.1109/ICESIT-ICICTES.2018.8442050","DOIUrl":"https://doi.org/10.1109/ICESIT-ICICTES.2018.8442050","url":null,"abstract":"A talking pen is the evolutional way of learning especially for children because it is fun and interactive. Commercial talking pen use a small infrared camera to capture the hidden dot patterns that hidden around a book's page. Specific sounds are generated according to the location of the pen on the pages. This image processing for recognition technique is complex and need calculation power because it had to calculate relative location and orientation of dots in a group. Although, the talking pen is successful product but it is not flexible to add new pattern or uses different set of patterns. In this research, the new approach for hidden dot pattern recognition is proposed. Convolutional neural networks or CNNs is selected as the recognition software. The system is built on Raspberry Pi Zero W hardware with Raspbian operating system and TensorFlow platform. MobileNet is used in the research since it small and effective for limited resources platform. MobileNet is trained by using the infrared images that captured by infrared camera module that connected to Raspberry Pi. Result shows that the accuracy of the proposed method is good enough and the response is fast enough to be implemented into the real-time commercial product and has ability to expand to any other kind of patterns without limit because the learned network can be updated easily without alter recognition software.","PeriodicalId":57136,"journal":{"name":"单片机与嵌入式系统应用","volume":"29 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78611699","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 : 2018-05-01DOI: 10.1109/ICESIT-ICICTES.2018.8442061
Pechlada Seenual, Thodsaporn Chay-intr, T. Theeramunkong
To fasten treebank construction, it is necessary to design an integrated annotation tool that includes word segmenter, sentence parser for initial tree suggestion, tree visualizer, tree-structure editor, and collaborative functions. In the past, existing tools did not consider an integrated platform that provides preprocessing, automated or semi-automated mechanism for parse tree suggestion, as well as tagged corpus data management. This paper presents a so-called CF Planter, a toolset for semi-automatic Thai treebank construction that consist of word segmenter, part-of-speech tagger, statistical parser, a web-based GUI for syntactic tree refinement and management. Given an input sentence, its most likely syntactic tree is automatically suggested and visualized to an annotator for manual correction before adding into the treebank repository. Whenever a new syntactic tree is appended into the treebank, the treebank repository is iteratively refined by computing a set of newly revised grammar rules based on revised probabilities. Toolset is performed to severally illustrate with grammar frequencies. The toolset facilitates annotators to easily tag tree structure for an input sentence. Finally, the process of automatic suggestion of syntactic tree is evaluated.
{"title":"CF Planter: A Toolset for Semi-automatic Thai Treebank Construction","authors":"Pechlada Seenual, Thodsaporn Chay-intr, T. Theeramunkong","doi":"10.1109/ICESIT-ICICTES.2018.8442061","DOIUrl":"https://doi.org/10.1109/ICESIT-ICICTES.2018.8442061","url":null,"abstract":"To fasten treebank construction, it is necessary to design an integrated annotation tool that includes word segmenter, sentence parser for initial tree suggestion, tree visualizer, tree-structure editor, and collaborative functions. In the past, existing tools did not consider an integrated platform that provides preprocessing, automated or semi-automated mechanism for parse tree suggestion, as well as tagged corpus data management. This paper presents a so-called CF Planter, a toolset for semi-automatic Thai treebank construction that consist of word segmenter, part-of-speech tagger, statistical parser, a web-based GUI for syntactic tree refinement and management. Given an input sentence, its most likely syntactic tree is automatically suggested and visualized to an annotator for manual correction before adding into the treebank repository. Whenever a new syntactic tree is appended into the treebank, the treebank repository is iteratively refined by computing a set of newly revised grammar rules based on revised probabilities. Toolset is performed to severally illustrate with grammar frequencies. The toolset facilitates annotators to easily tag tree structure for an input sentence. Finally, the process of automatic suggestion of syntactic tree is evaluated.","PeriodicalId":57136,"journal":{"name":"单片机与嵌入式系统应用","volume":"9 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82483546","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}
The scope of Business Intelligence (BI) has been extended from strategic questions to operational tasks. In this way, the requests for updating the data in reports are generated. Consequently, BI specialists, who are responsible for preparing the data, become insufficient. A Self-Service BI has been introduced to allow non-specialists to derive the information from the large amounts of data without involving BI specialists. In this work, the data preparation for self-service BI for producing human resources reports of a bank is presented. A number of views is created based on the mapped attributes in the data warehouse and the requirements. Then, a data cube is constructed from the SQL command of the views. The configuration of dimensions and measures in BI software allows non-specialists to perform reporting and analytics from a variety of viewpoints. The outcome of the data preparation for BI software allows the non-specialists to produce time-critical reports without involving the BI specialists.
{"title":"Data Preparation for Self-Service BI of Human Resources Analysis in Banking Industry","authors":"Navaphat Bhichesthapong, Mananya Jongkolpatlr, Tanapond Praikasate, Natsuda Kaothanthong","doi":"10.1109/ICESIT-ICICTES.2018.8442065","DOIUrl":"https://doi.org/10.1109/ICESIT-ICICTES.2018.8442065","url":null,"abstract":"The scope of Business Intelligence (BI) has been extended from strategic questions to operational tasks. In this way, the requests for updating the data in reports are generated. Consequently, BI specialists, who are responsible for preparing the data, become insufficient. A Self-Service BI has been introduced to allow non-specialists to derive the information from the large amounts of data without involving BI specialists. In this work, the data preparation for self-service BI for producing human resources reports of a bank is presented. A number of views is created based on the mapped attributes in the data warehouse and the requirements. Then, a data cube is constructed from the SQL command of the views. The configuration of dimensions and measures in BI software allows non-specialists to perform reporting and analytics from a variety of viewpoints. The outcome of the data preparation for BI software allows the non-specialists to produce time-critical reports without involving the BI specialists.","PeriodicalId":57136,"journal":{"name":"单片机与嵌入式系统应用","volume":"57 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81489905","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：