Received Signal Strength Indicator (RSSI) is used in indoor positioning for measuring object distance to the base station. However, acquiring accurate RSSI values is challenging because wireless interference factors, such as multipath decline interference, make RSSI values of the same object fluctuate over time. Therefore, instead of a single RSSI, RSSI acquisition will collect a set of RSSI values from which the most moderate RSSI is derived. For this purpose, we propose an Enhanced Gaussian Mixture Model (EGMM) to derive a more precise RSSI for improving indoor positioning accuracy. EGMM enhances Gaussian Mixture Model (GMM) by applying Akaike information criterion (AIC) to determine the best K value for GMM to divide RSSI values into K sets representing signals from different paths. Then, EGMM identifies the most appropriate set of RSSI values to derive a more precise RSSI and thus improves the accuracy of indoor positioning. Our EGMM solution performs well in an open indoor space. The experiment is conducted with iBeacon devices, and the average error distance of EGMM is about 64% of those generated by existing Gaussian filtering. The average positioning error of EGMM is about 0.48 meter, which is adequate to indoor positioning accuracy.
RSSI (Received Signal Strength Indicator)用于室内定位，用于测量目标到基站的距离。然而，获取准确的RSSI值具有挑战性，因为无线干扰因素，如多径衰落干扰，会使同一对象的RSSI值随时间波动。因此，RSSI采集将收集一组RSSI值，而不是单个RSSI，从中派生出最适中的RSSI。为此，我们提出了一种增强高斯混合模型(EGMM)，以获得更精确的RSSI，以提高室内定位精度。EGMM对高斯混合模型(GMM)进行了改进，利用赤池信息准则(Akaike information criterion, AIC)确定GMM的最佳K值，将RSSI值划分为代表不同路径信号的K集。然后，EGMM识别最合适的RSSI值集合，得到更精确的RSSI，从而提高室内定位的精度。我们的EGMM解决方案在开放的室内空间中表现良好。在iBeacon设备上进行实验，EGMM的平均误差距离约为现有高斯滤波的64%。EGMM的平均定位误差约为0.48 m，足以满足室内定位精度。
{"title":"Enhanced Gaussian Mixture Model for Indoor Positioning Accuracy","authors":"C. Tseng, Jing-Shyang Yen","doi":"10.1109/ICS.2016.0099","DOIUrl":"https://doi.org/10.1109/ICS.2016.0099","url":null,"abstract":"Received Signal Strength Indicator (RSSI) is used in indoor positioning for measuring object distance to the base station. However, acquiring accurate RSSI values is challenging because wireless interference factors, such as multipath decline interference, make RSSI values of the same object fluctuate over time. Therefore, instead of a single RSSI, RSSI acquisition will collect a set of RSSI values from which the most moderate RSSI is derived. For this purpose, we propose an Enhanced Gaussian Mixture Model (EGMM) to derive a more precise RSSI for improving indoor positioning accuracy. EGMM enhances Gaussian Mixture Model (GMM) by applying Akaike information criterion (AIC) to determine the best K value for GMM to divide RSSI values into K sets representing signals from different paths. Then, EGMM identifies the most appropriate set of RSSI values to derive a more precise RSSI and thus improves the accuracy of indoor positioning. Our EGMM solution performs well in an open indoor space. The experiment is conducted with iBeacon devices, and the average error distance of EGMM is about 64% of those generated by existing Gaussian filtering. The average positioning error of EGMM is about 0.48 meter, which is adequate to indoor positioning accuracy.","PeriodicalId":281088,"journal":{"name":"2016 International Computer Symposium (ICS)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132240245","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 non-linear, unstable system of the two wheeled self-balancing robot has made it a popular research subject within the past decade. This paper outlines the design of a two wheeled robot with self balancing control systems using Reinforcement Learning. The BeagleBone Black platform was used to design the two wheeled robot. Along with the motor, the robot was also equipped with an accelerometer and gyroscope. Using the Q-Learning method, adjustments to the motor were made according to the dip angle and the angular velocity at that given time to return the robot to balance. The experimental results show that using this reinforcement learning method, the robot has the ability to quickly return to a balanced state under any dip angle.
{"title":"Using Reinforcement Learning to Achieve Two Wheeled Self Balancing Control","authors":"Ching-Lung Chang, Shih-Yu Chang","doi":"10.1109/ICS.2016.0029","DOIUrl":"https://doi.org/10.1109/ICS.2016.0029","url":null,"abstract":"The non-linear, unstable system of the two wheeled self-balancing robot has made it a popular research subject within the past decade. This paper outlines the design of a two wheeled robot with self balancing control systems using Reinforcement Learning. The BeagleBone Black platform was used to design the two wheeled robot. Along with the motor, the robot was also equipped with an accelerometer and gyroscope. Using the Q-Learning method, adjustments to the motor were made according to the dip angle and the angular velocity at that given time to return the robot to balance. The experimental results show that using this reinforcement learning method, the robot has the ability to quickly return to a balanced state under any dip angle.","PeriodicalId":281088,"journal":{"name":"2016 International Computer Symposium (ICS)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134164030","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}
Due to the sheer volume of opinion rich web resources such as discussion forum, review sites, blogs, and news corpora available in digital form, much of the current research is focusing on the area of sentiment analysis. People are intended to develop a system that can identify and classify opinion or sentiment as represented in an electronic text. An accurate method for predicting sentiments could enable us, to extract opinions from the internet and predict on-line customer's preferences, which could prove valuable for economic or marketing research. In this paper we present a framework for opinion mining in Traditional Chinese-called FOM (Framework of Opinion Mining) to collect unstructured articles in the popular web site and analyse the opinion and sentiment in the semi-automatic way. The framework is developed by objected oriented design patterns, such as to support the flexibility and maintainability. With the FOM framework, new analysis algorithm can be easily replaced and integrated in a new application. A flood predication application based on facebook text in Taiwan will be demonstrated in this paper.
由于大量的意见丰富的网络资源，如论坛，评论网站，博客和新闻语料库的数字形式，目前的许多研究都集中在情感分析领域。人们打算开发一种系统，可以识别和分类电子文本中所代表的意见或情绪。一种准确的预测情绪的方法可以使我们能够从互联网上提取意见，并预测在线客户的偏好，这对经济或营销研究来说是有价值的。本文提出了一种观点挖掘框架，即FOM (framework of opinion mining)，用于在热门网站中收集非结构化文章，并以半自动的方式分析观点和情感。该框架采用面向对象的设计模式开发，以支持灵活性和可维护性等。利用FOM框架，可以方便地替换和集成新的分析算法。本文将演示一个基于facebook文本的台湾洪水预测应用程序。
{"title":"A Framework for Opinion Mining System with Design Pattern","authors":"Nien-Lin Hsueh","doi":"10.1109/ICS.2016.0128","DOIUrl":"https://doi.org/10.1109/ICS.2016.0128","url":null,"abstract":"Due to the sheer volume of opinion rich web resources such as discussion forum, review sites, blogs, and news corpora available in digital form, much of the current research is focusing on the area of sentiment analysis. People are intended to develop a system that can identify and classify opinion or sentiment as represented in an electronic text. An accurate method for predicting sentiments could enable us, to extract opinions from the internet and predict on-line customer's preferences, which could prove valuable for economic or marketing research. In this paper we present a framework for opinion mining in Traditional Chinese-called FOM (Framework of Opinion Mining) to collect unstructured articles in the popular web site and analyse the opinion and sentiment in the semi-automatic way. The framework is developed by objected oriented design patterns, such as to support the flexibility and maintainability. With the FOM framework, new analysis algorithm can be easily replaced and integrated in a new application. A flood predication application based on facebook text in Taiwan will be demonstrated in this paper.","PeriodicalId":281088,"journal":{"name":"2016 International Computer Symposium (ICS)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129024759","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 objective of visual cryptography is to hide secret in multiple share images. Then, stacking share images together decrypts hidden secret by human visual system. As the share images are given with different priorities, those share images hide various degrees of secret, which is the objective of progressive visual cryptography. This paper presents a scheme to realize progressive visual cryptography. A 2x2 block is the basic element of share image, and we design block pairs for secret hiding as well as secret encryption. The degrees of hidden secret depend on the priorities of share images. The proposed scheme is capable of decrypting partial secret and inferring the stacked shares. The experiment results will demonstrate that our scheme further achieves applications based on progressive visual cryptography, including self-decryption watermark, and inference of shares stacking.
{"title":"Inference of Share Stacking Based on Progressive Visual Cryptography","authors":"Y. Zeng, Wen-Tsung Chang","doi":"10.1109/ICS.2016.0054","DOIUrl":"https://doi.org/10.1109/ICS.2016.0054","url":null,"abstract":"The objective of visual cryptography is to hide secret in multiple share images. Then, stacking share images together decrypts hidden secret by human visual system. As the share images are given with different priorities, those share images hide various degrees of secret, which is the objective of progressive visual cryptography. This paper presents a scheme to realize progressive visual cryptography. A 2x2 block is the basic element of share image, and we design block pairs for secret hiding as well as secret encryption. The degrees of hidden secret depend on the priorities of share images. The proposed scheme is capable of decrypting partial secret and inferring the stacked shares. The experiment results will demonstrate that our scheme further achieves applications based on progressive visual cryptography, including self-decryption watermark, and inference of shares stacking.","PeriodicalId":281088,"journal":{"name":"2016 International Computer Symposium (ICS)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126112854","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}
Cloud storage supplies enormous convenience for numerous companies and individuals to manage their data. However, data owners lose ultimately physical control of their data, which introduces many potential safety hazards in the cloud storage environment. Many scholars have made studies on the security problem of cloud storage data. To solve the problem, we propose a secure audit scheme supporting dynamic operation and transparent verification. Utilizing BLS short signature as well as the sequence-enforced B+ Hash Tree structure, the audit scheme is more effective. The scheme introduces an organizer in the auditing process to prevent the TPA from getting any information about the data's location. Thus, the scheme is completely transparent for TPA. Meanwhile, the scheme utilizes random mask and bilinear aggregate signature technology to realize privacy protection and batch audit.
{"title":"An Efficient and Secure Public Batch Auditing Protocol for Dynamic Cloud Storage Data","authors":"Liu Yang, Lili Xia","doi":"10.1109/ICS.2016.0138","DOIUrl":"https://doi.org/10.1109/ICS.2016.0138","url":null,"abstract":"Cloud storage supplies enormous convenience for numerous companies and individuals to manage their data. However, data owners lose ultimately physical control of their data, which introduces many potential safety hazards in the cloud storage environment. Many scholars have made studies on the security problem of cloud storage data. To solve the problem, we propose a secure audit scheme supporting dynamic operation and transparent verification. Utilizing BLS short signature as well as the sequence-enforced B+ Hash Tree structure, the audit scheme is more effective. The scheme introduces an organizer in the auditing process to prevent the TPA from getting any information about the data's location. Thus, the scheme is completely transparent for TPA. Meanwhile, the scheme utilizes random mask and bilinear aggregate signature technology to realize privacy protection and batch audit.","PeriodicalId":281088,"journal":{"name":"2016 International Computer Symposium (ICS)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125828744","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}
This paper reports a requirements engineering approach to attribute selection for enhancing the results of a recommendation system. A recommendation system suffers the sparsity problem and the cold start problem with collaborative filtering which are caused by the lack of data. Our method is to introduce more timely information of user preferences to enhance the recommendation results that meet the current needs of a user. The proposed method uses a goal-driven approach with the support of the Analytic Hierarchy Process in attribute selection. The experiments show that this method derives promising results.
{"title":"A Goal-Driven Attribute Selection Method for Recommendation Systems","authors":"Ching-Jung Lee, Alan Liu, Po-Hsuan Lu, Power Wu","doi":"10.1109/ICS.2016.0118","DOIUrl":"https://doi.org/10.1109/ICS.2016.0118","url":null,"abstract":"This paper reports a requirements engineering approach to attribute selection for enhancing the results of a recommendation system. A recommendation system suffers the sparsity problem and the cold start problem with collaborative filtering which are caused by the lack of data. Our method is to introduce more timely information of user preferences to enhance the recommendation results that meet the current needs of a user. The proposed method uses a goal-driven approach with the support of the Analytic Hierarchy Process in attribute selection. The experiments show that this method derives promising results.","PeriodicalId":281088,"journal":{"name":"2016 International Computer Symposium (ICS)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121629418","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 response to the technological development in recent years, many technology giants are making efforts toward Industry 4.0. However, many small-and medium-sized factories cannot even computerize and automate their factories, which is the foundation of Industry 4.0, due to inadequate capital and scale. This is because the majority of these factories are still using conventional machines in which the data cannot be digitized. Consequently, they cannot achieve the goal of Industry 4.0. This work therefore proposes a simple approach that facilitates the transition of these small-and medium-sized factories. The approach uses add-on triaxial sensors to aid in machine monitoring. The data obtained is analyzed for abnormalities using neural networks. Experiment results demonstrate the validity of the proposed approach.
{"title":"New Method for Industry 4.0 Machine Status Prediction - A Case Study with the Machine of a Spring Factory","authors":"Tzu-Yu Lin, Yo-Ming Chen, Don-Lin Yang, Yi-Chung Chen","doi":"10.1109/ICS.2016.0071","DOIUrl":"https://doi.org/10.1109/ICS.2016.0071","url":null,"abstract":"In response to the technological development in recent years, many technology giants are making efforts toward Industry 4.0. However, many small-and medium-sized factories cannot even computerize and automate their factories, which is the foundation of Industry 4.0, due to inadequate capital and scale. This is because the majority of these factories are still using conventional machines in which the data cannot be digitized. Consequently, they cannot achieve the goal of Industry 4.0. This work therefore proposes a simple approach that facilitates the transition of these small-and medium-sized factories. The approach uses add-on triaxial sensors to aid in machine monitoring. The data obtained is analyzed for abnormalities using neural networks. Experiment results demonstrate the validity of the proposed approach.","PeriodicalId":281088,"journal":{"name":"2016 International Computer Symposium (ICS)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124792327","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}
Task ranking and allocation are two major steps in list-based workflow scheduling. This paper explores various possibilities, evaluates recent approaches in the literature, and proposes several new task ranking and allocation heuristics. A series of simulation experiments have been conducted to evaluate the proposed heuristics. Experimental results indicate that effectiveness of task ranking and allocation heuristics largely depends on the characteristics of workflows to be scheduled, and our new scheduling heuristics can outperform previous methods when dealing with workflows of high CCR (Communication-to-Computation Ratio) values.
{"title":"Task Ranking and Allocation Heuristics for Efficient Workflow Schedules","authors":"Kuo-Chan Huang, Meng-Han Tsai","doi":"10.1109/ICS.2016.0108","DOIUrl":"https://doi.org/10.1109/ICS.2016.0108","url":null,"abstract":"Task ranking and allocation are two major steps in list-based workflow scheduling. This paper explores various possibilities, evaluates recent approaches in the literature, and proposes several new task ranking and allocation heuristics. A series of simulation experiments have been conducted to evaluate the proposed heuristics. Experimental results indicate that effectiveness of task ranking and allocation heuristics largely depends on the characteristics of workflows to be scheduled, and our new scheduling heuristics can outperform previous methods when dealing with workflows of high CCR (Communication-to-Computation Ratio) values.","PeriodicalId":281088,"journal":{"name":"2016 International Computer Symposium (ICS)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125000198","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 present a continuous deep learning model for fall detection using Microsoft Kinect. The input include pre-processed high-resolution RGB images, depth images collected by a Kinect and optical flow images. We combine several deep learning structures including convolutional neural networks and long short-term memory networks for continuous human fallen detection. Finally, we present experimental results to demonstrate the performance and utility of our approach.
{"title":"Abnormal Event Detection Using Microsoft Kinect in a Smart Home","authors":"Hsiu-Yu Lin, Yu-Ling Hsueh, W. Lie","doi":"10.1109/ICS.2016.0064","DOIUrl":"https://doi.org/10.1109/ICS.2016.0064","url":null,"abstract":"In this paper, we present a continuous deep learning model for fall detection using Microsoft Kinect. The input include pre-processed high-resolution RGB images, depth images collected by a Kinect and optical flow images. We combine several deep learning structures including convolutional neural networks and long short-term memory networks for continuous human fallen detection. Finally, we present experimental results to demonstrate the performance and utility of our approach.","PeriodicalId":281088,"journal":{"name":"2016 International Computer Symposium (ICS)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125018105","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}
An extension to the design domain of problem frames has been proposed. The proposed extension is intended to cope with the inclusion of lexical design domains that have physical counterparts with the equivalent information. An example of the use of such a physical counterpart is illustrated with a spot service application in patient monitoring.
{"title":"Expressing Requirements of Spot Services in Problem Frames: Design Domains as Physical-Lexical Domains","authors":"Chin-Yun Hsieh, Yu Chin Cheng, J. Jwo","doi":"10.1109/ICS.2016.0117","DOIUrl":"https://doi.org/10.1109/ICS.2016.0117","url":null,"abstract":"An extension to the design domain of problem frames has been proposed. The proposed extension is intended to cope with the inclusion of lexical design domains that have physical counterparts with the equivalent information. An example of the use of such a physical counterpart is illustrated with a spot service application in patient monitoring.","PeriodicalId":281088,"journal":{"name":"2016 International Computer Symposium (ICS)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122143099","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：