Yu Lu, Alice Miller, Chris W. Johnson, Zhaoguang Peng, T. Zhao
This paper highlights an application of probabilistic model checking to satellite positioning systems for aircraft guidance. After introducing our formal approach based on using the PRISM model checker, we built a model of a global navigation satellite system (GNSS) based positioning system for a specific flight in the probabilistic π-calculus, a process algebra which supports modelling of concurrency, uncertainty, and mobility. After that, we encode our model into the PRISM language. We then analyse the availability properties that relate to the dependability and overall performance of the underlying system. The aim of our research is to use PRISM to assist industrial designers and developers of the GNSS.
{"title":"Availability Analysis of Satellite Positioning Systems for Aviation Using the PRISM Model Checker","authors":"Yu Lu, Alice Miller, Chris W. Johnson, Zhaoguang Peng, T. Zhao","doi":"10.1109/CSE.2014.148","DOIUrl":"https://doi.org/10.1109/CSE.2014.148","url":null,"abstract":"This paper highlights an application of probabilistic model checking to satellite positioning systems for aircraft guidance. After introducing our formal approach based on using the PRISM model checker, we built a model of a global navigation satellite system (GNSS) based positioning system for a specific flight in the probabilistic π-calculus, a process algebra which supports modelling of concurrency, uncertainty, and mobility. After that, we encode our model into the PRISM language. We then analyse the availability properties that relate to the dependability and overall performance of the underlying system. The aim of our research is to use PRISM to assist industrial designers and developers of the GNSS.","PeriodicalId":258990,"journal":{"name":"2014 IEEE 17th International Conference on Computational Science and Engineering","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115645893","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In recent years, the focus to optimize network transmission efficiency has evolved to adopt methods that let those intermediate data transferring nodes get involved with routing, forwarding and caching. In other words, the new network architecture designs become in favor of hop-to-hop model, instead of traditional TCP-like end-to-end model. Named data networking is a promising future internet data oriented architecture which uses names instead of addresses and exchanges or forwards interest/data pair packets at each node along the path to route data for delivery. And meanwhile Network coding (NC) is a content oriented and effective method to reduce redundancy, increase network throughput and improve robustness. Nonetheless, due to NDN's current preliminary research, less research has combined these two technologies together. This paper presents some new thoughts to study on the benefits brought by integrating network coding to NDN, which can effectively improve network utilization, strengthen caching privacy, and also promote development of the NDN architecture itself.
{"title":"Exploring the Benefits of Introducing Network Coding into Named Data Networking","authors":"Kai Lei, Tao Chen, Chen Peng, Zhi Tan","doi":"10.1109/CSE.2014.128","DOIUrl":"https://doi.org/10.1109/CSE.2014.128","url":null,"abstract":"In recent years, the focus to optimize network transmission efficiency has evolved to adopt methods that let those intermediate data transferring nodes get involved with routing, forwarding and caching. In other words, the new network architecture designs become in favor of hop-to-hop model, instead of traditional TCP-like end-to-end model. Named data networking is a promising future internet data oriented architecture which uses names instead of addresses and exchanges or forwards interest/data pair packets at each node along the path to route data for delivery. And meanwhile Network coding (NC) is a content oriented and effective method to reduce redundancy, increase network throughput and improve robustness. Nonetheless, due to NDN's current preliminary research, less research has combined these two technologies together. This paper presents some new thoughts to study on the benefits brought by integrating network coding to NDN, which can effectively improve network utilization, strengthen caching privacy, and also promote development of the NDN architecture itself.","PeriodicalId":258990,"journal":{"name":"2014 IEEE 17th International Conference on Computational Science and Engineering","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115711740","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 Random Forests algorithm belongs to the class of ensemble learning methods, which are common used in classification problem. In this paper, we studied the problem of adopting the Random Forests algorithm to learn raw data from real usage scenario. An improvement, which is stable, strict, high efficient, data-driven, problem independent and has no impact on algorithm performance, is proposed to investigate 2 actual issues of feature selection of the Random Forests algorithm. The first one is to eliminate noisy features, which are irrelevant to the classification. And the second one is to eliminate redundant features, which are highly relevant with other features, but useless. We implemented our improvement approach on Spark. Experiments are performed to evaluate our improvement and the results show that our approach has an ideal performance.
{"title":"An Improvement to Feature Selection of Random Forests on Spark","authors":"Ke Sun, Wansheng Miao, Xin Zhang, Ruonan Rao","doi":"10.1109/CSE.2014.159","DOIUrl":"https://doi.org/10.1109/CSE.2014.159","url":null,"abstract":"The Random Forests algorithm belongs to the class of ensemble learning methods, which are common used in classification problem. In this paper, we studied the problem of adopting the Random Forests algorithm to learn raw data from real usage scenario. An improvement, which is stable, strict, high efficient, data-driven, problem independent and has no impact on algorithm performance, is proposed to investigate 2 actual issues of feature selection of the Random Forests algorithm. The first one is to eliminate noisy features, which are irrelevant to the classification. And the second one is to eliminate redundant features, which are highly relevant with other features, but useless. We implemented our improvement approach on Spark. Experiments are performed to evaluate our improvement and the results show that our approach has an ideal performance.","PeriodicalId":258990,"journal":{"name":"2014 IEEE 17th International Conference on Computational Science and Engineering","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115829006","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}
Credit risk analysis plays an important role in the financial market. In this paper, discriminative restricted Boltzmann machine (RBM) is used in credit risk classification. RBM is a generative model associated with an undirected graph, which can capture complicated features from observed data, and after introducing discriminative component into RBM, it can be used to train a non-linear classifier. The method is tested in a real-world credit risk prediction task, and the empirical results demonstrate the advantage of the method over other competing ones.
{"title":"Credit Risk Classification Using Discriminative Restricted Boltzmann Machines","authors":"Qiaochu Li, Jian Zhang, Yuhan Wang, Kary Kang","doi":"10.1109/CSE.2014.312","DOIUrl":"https://doi.org/10.1109/CSE.2014.312","url":null,"abstract":"Credit risk analysis plays an important role in the financial market. In this paper, discriminative restricted Boltzmann machine (RBM) is used in credit risk classification. RBM is a generative model associated with an undirected graph, which can capture complicated features from observed data, and after introducing discriminative component into RBM, it can be used to train a non-linear classifier. The method is tested in a real-world credit risk prediction task, and the empirical results demonstrate the advantage of the method over other competing ones.","PeriodicalId":258990,"journal":{"name":"2014 IEEE 17th International Conference on Computational Science and Engineering","volume":"2021 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127464044","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}
Mohamed Y. E. Simik, Feng Chi, A. M. Abdelgader, Randa S. I. Saleh
Bleeding is blood escaping from the circulatory system. The complete loss of blood causes death. Stopping bleeding is an important part of both first aid and surgery. This paper presents an automated bleeding detector and alarm system using an advanced RF transceiver and GSM system to sound an alarm on the detection of moisture in the medical gauze. The bleeding sensor detector consists of an elongated pair of fine conductors positioned between the layers of a medical gauze in a region liable to witness bleeding. The end of the sensor protrudes from the upper front portion of the medical gauze and terminates at pressing studs. A bleeding detector unit and RF transmitter are adapted to be easily coupled to the protruding end of the elongated sensor and configured to monitor the electrical resistance between the spaced conductors of the detector. When the medical gauze is wet with blood, the resistance between the spaced conductors falls below a pre established value. Consequently, RF transmitter sends a wireless signal to the RF receiver and GSM system to produce the alarm informing intended persons of the bleeding.
{"title":"Design of Simple Bleeding Detector and Alarm System Using RF Transceiver and GSM System","authors":"Mohamed Y. E. Simik, Feng Chi, A. M. Abdelgader, Randa S. I. Saleh","doi":"10.1109/CSE.2014.255","DOIUrl":"https://doi.org/10.1109/CSE.2014.255","url":null,"abstract":"Bleeding is blood escaping from the circulatory system. The complete loss of blood causes death. Stopping bleeding is an important part of both first aid and surgery. This paper presents an automated bleeding detector and alarm system using an advanced RF transceiver and GSM system to sound an alarm on the detection of moisture in the medical gauze. The bleeding sensor detector consists of an elongated pair of fine conductors positioned between the layers of a medical gauze in a region liable to witness bleeding. The end of the sensor protrudes from the upper front portion of the medical gauze and terminates at pressing studs. A bleeding detector unit and RF transmitter are adapted to be easily coupled to the protruding end of the elongated sensor and configured to monitor the electrical resistance between the spaced conductors of the detector. When the medical gauze is wet with blood, the resistance between the spaced conductors falls below a pre established value. Consequently, RF transmitter sends a wireless signal to the RF receiver and GSM system to produce the alarm informing intended persons of the bleeding.","PeriodicalId":258990,"journal":{"name":"2014 IEEE 17th International Conference on Computational Science and Engineering","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125949877","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}
Yuan Yuan, Changhai Wang, Jianzhong Zhang, Jingdong Xu, Meng Li
Activity recognition with triaxial accelerometer embedded in mobile phone is an important research topic in pervasive computing field. The research results can be widely used in many healthcare or data mining applications. Numerous classification algorithms have been applied into the activity recognition tasks. Among these algorithms, ELM (Extreme Learning Machine) shows its advantages in generalization performance and learning speed. But because of the randomly generated hidden layer parameters, ELM classifiers usually produce unstable predictions. To construct a more stable classifier for our mobile-phone based activity recognition task, we designed an ensemble learning algorithm called Average Combining Extreme Learning Machine (ACELM), which integrates several independent ELM classifiers by averaging their outputs. To evaluate the algorithm, we collected raw accelerometer data of five daily activities from mobile phones carried by volunteers, and used them to train and test our classifier. The experiment results show that our algorithm has greatly improved the general performance of ELM in mobile-phone based activity recognition task.
{"title":"An Ensemble Approach for Activity Recognition with Accelerometer in Mobile-Phone","authors":"Yuan Yuan, Changhai Wang, Jianzhong Zhang, Jingdong Xu, Meng Li","doi":"10.1109/CSE.2014.274","DOIUrl":"https://doi.org/10.1109/CSE.2014.274","url":null,"abstract":"Activity recognition with triaxial accelerometer embedded in mobile phone is an important research topic in pervasive computing field. The research results can be widely used in many healthcare or data mining applications. Numerous classification algorithms have been applied into the activity recognition tasks. Among these algorithms, ELM (Extreme Learning Machine) shows its advantages in generalization performance and learning speed. But because of the randomly generated hidden layer parameters, ELM classifiers usually produce unstable predictions. To construct a more stable classifier for our mobile-phone based activity recognition task, we designed an ensemble learning algorithm called Average Combining Extreme Learning Machine (ACELM), which integrates several independent ELM classifiers by averaging their outputs. To evaluate the algorithm, we collected raw accelerometer data of five daily activities from mobile phones carried by volunteers, and used them to train and test our classifier. The experiment results show that our algorithm has greatly improved the general performance of ELM in mobile-phone based activity recognition task.","PeriodicalId":258990,"journal":{"name":"2014 IEEE 17th International Conference on Computational Science and Engineering","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116155309","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}
Popular techniques used in today's Web search engines and digital libraries for retrieving and ranking scientific publications have foundations in modern information retrieval. Information and users in the scientific research communities have their own characteristics, however, they have not been sufficiently exploited in existing retrieval and ranking methods. We present a semantic search engine, IRIS2, which represents the semantic entities and their relations using ontologies and knowledge bases. It utilises a ranking method based on the "rational research" model, which restores an elegant idea that a researcher does rational research in an academic environment. We explain in detail the design and implementation of the IRIS2 prototype and compare its retrieving and ranking performance with existing methods.
{"title":"IRIS2: A Semantic Search Engine That Does Rational Research","authors":"Wei Wang, Hai-Ning Liang","doi":"10.1109/CSE.2014.62","DOIUrl":"https://doi.org/10.1109/CSE.2014.62","url":null,"abstract":"Popular techniques used in today's Web search engines and digital libraries for retrieving and ranking scientific publications have foundations in modern information retrieval. Information and users in the scientific research communities have their own characteristics, however, they have not been sufficiently exploited in existing retrieval and ranking methods. We present a semantic search engine, IRIS2, which represents the semantic entities and their relations using ontologies and knowledge bases. It utilises a ranking method based on the \"rational research\" model, which restores an elegant idea that a researcher does rational research in an academic environment. We explain in detail the design and implementation of the IRIS2 prototype and compare its retrieving and ranking performance with existing methods.","PeriodicalId":258990,"journal":{"name":"2014 IEEE 17th International Conference on Computational Science and Engineering","volume":"139 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122582586","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}
For a given edge-weighted graph G = (V, E, w), in which the vertices are partitioned into clusters R = {R1, R2, ... , Rk}, a spanning tree of G is a clustered spanning tree if the subtrees spanning the clusters are mutually disjoint. In this paper we study the problem of constructing a clustered spanning tree such that the total distance summed over all vertices of different clusters is minimized. We show that the problem is polynomial-time solvable when the number of clusters k is 2 and NP-hard for k = 3. We also present a 2-approximation algorithm for the case of 3 clusters.
{"title":"Clustered Trees with Minimum Inter-cluster Distance","authors":"B. Wu, Chen-Wan Lin","doi":"10.1109/CSE.2014.223","DOIUrl":"https://doi.org/10.1109/CSE.2014.223","url":null,"abstract":"For a given edge-weighted graph G = (V, E, w), in which the vertices are partitioned into clusters R = {R1, R2, ... , Rk}, a spanning tree of G is a clustered spanning tree if the subtrees spanning the clusters are mutually disjoint. In this paper we study the problem of constructing a clustered spanning tree such that the total distance summed over all vertices of different clusters is minimized. We show that the problem is polynomial-time solvable when the number of clusters k is 2 and NP-hard for k = 3. We also present a 2-approximation algorithm for the case of 3 clusters.","PeriodicalId":258990,"journal":{"name":"2014 IEEE 17th International Conference on Computational Science and Engineering","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122038839","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}
Web users display their preferences implicitly by a sequence of pages they navigated. Web recommendation systems use methods to extract useful knowledge about user interests from such data. We propose a Bayesian nonparametric approach to the problem of modeling user interests in recommender systems using implicit feedback like user navigations and clicks on items. Our approach is based on the discovery of a set of latent interests that are shared among users in the system and make a key assumption that each user activity is motivated only by several interests amongst user interest profile which is quite different from most of the existing recommendation algorithms. By using a beta process and a Dirichlet prior, the number of hidden interests and the relationships between interests and items are both inferred from the data. In order to model the sequential information on user's visits, we make a Markovian assumption on each user's navigated item sequence. We develop a Markov chain Monte Carlo inference method based on the Indian buffet process representation of the beta process. We validate our sampling algorithm using synthetic data and real world datasets to demonstrate promising results on recovering the hidden user interests.
{"title":"A Bayesian Nonparametric Topic Model for User Interest Modeling","authors":"Qinjiao Mao, B. Feng, Shanliang Pan","doi":"10.1109/CSE.2014.122","DOIUrl":"https://doi.org/10.1109/CSE.2014.122","url":null,"abstract":"Web users display their preferences implicitly by a sequence of pages they navigated. Web recommendation systems use methods to extract useful knowledge about user interests from such data. We propose a Bayesian nonparametric approach to the problem of modeling user interests in recommender systems using implicit feedback like user navigations and clicks on items. Our approach is based on the discovery of a set of latent interests that are shared among users in the system and make a key assumption that each user activity is motivated only by several interests amongst user interest profile which is quite different from most of the existing recommendation algorithms. By using a beta process and a Dirichlet prior, the number of hidden interests and the relationships between interests and items are both inferred from the data. In order to model the sequential information on user's visits, we make a Markovian assumption on each user's navigated item sequence. We develop a Markov chain Monte Carlo inference method based on the Indian buffet process representation of the beta process. We validate our sampling algorithm using synthetic data and real world datasets to demonstrate promising results on recovering the hidden user interests.","PeriodicalId":258990,"journal":{"name":"2014 IEEE 17th International Conference on Computational Science and Engineering","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116810394","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}
One of the fundamentally required services in the grid environment is resource discovery. The discovery involves the search for appropriate resources that match user requirements. An efficient mechanism for this service still remains a crucial problem especially within a dynamic and scalable environment such as the grid. Majority of the proposed solutions based on centralized and hierarchical approaches suffer from shortcomings ranging from single point of failure to network congestion. In this paper, we propose a resource discovery mechanism that relies on the activities of an agent during peak request hours in a peer-to-peer (P2P) based grid system. The agent searches and learns the paths to requested resources with associated maximum rewards. These paths are managed by the super-node for subsequent resource discovery requests. We evaluated the performance of the proposed approach against some resource discovery approaches. The results show an improved performance in the proposed algorithm over the Time To Live (TTL) and and Adjacency List and Ant Colony Algorithm (GAA).
{"title":"Agent Based Resource Discovery for Peak Request Periods in Peer-to-Peer Grid Infrastructures","authors":"Moses Olaifa, R. V. D. Merwe, T. Mapayi","doi":"10.1109/CSE.2014.199","DOIUrl":"https://doi.org/10.1109/CSE.2014.199","url":null,"abstract":"One of the fundamentally required services in the grid environment is resource discovery. The discovery involves the search for appropriate resources that match user requirements. An efficient mechanism for this service still remains a crucial problem especially within a dynamic and scalable environment such as the grid. Majority of the proposed solutions based on centralized and hierarchical approaches suffer from shortcomings ranging from single point of failure to network congestion. In this paper, we propose a resource discovery mechanism that relies on the activities of an agent during peak request hours in a peer-to-peer (P2P) based grid system. The agent searches and learns the paths to requested resources with associated maximum rewards. These paths are managed by the super-node for subsequent resource discovery requests. We evaluated the performance of the proposed approach against some resource discovery approaches. The results show an improved performance in the proposed algorithm over the Time To Live (TTL) and and Adjacency List and Ant Colony Algorithm (GAA).","PeriodicalId":258990,"journal":{"name":"2014 IEEE 17th International Conference on Computational Science and Engineering","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129869606","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：