9th IEEE International Conference on Cognitive Informatics (ICCI'10)最新文献

{"title":"Development of a knowledge-based system for monitoring and diagnosis of the CO2 capture process","authors":"Qing Zhou, Christine W. Chan, P. Tontiwachwuthikul","doi":"10.1109/COGINF.2010.5599717","DOIUrl":"https://doi.org/10.1109/COGINF.2010.5599717","url":null,"abstract":"The amine-based post combustion carbon dioxide (CO2) capture has become a widely adopted technology for reducing large-scale CO2 emissions, thereby helping to mitigate global warming. The operation of amine-based CO2 capture is a complicated task, which involves monitoring over one hundred process parameters and manipulation of numerous valves and pumps. To enhance CO2 capture efficiency, artificial intelligence techniques were applied to develop a knowledge-based expert system for monitoring and control of the CO2 capture process. To develop the knowledge base, the Inferential Modeling Technique (IMT) was applied to analyze the domain knowledge and problem-solving techniques, and the system was implemented on DeltaV Simulate. The expert system helps to enhance performance and efficiency of the CO2 capture system by reducing the time for diagnosis if an abnormal condition occurs. The expert system can also be used as a decision-support tool to help inexperienced operators in process control and can be used for training novice operators. The knowledge base can be extended with future development of the system.","PeriodicalId":365083,"journal":{"name":"9th IEEE International Conference on Cognitive Informatics (ICCI'10)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129930469","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}

{"title":"Fuzzy Multi-Class Support Vector Machines for cooperative network intrusion detection","authors":"Wei Zhang, Shaohua Teng, Haibin Zhu, Hongle Du, Xiaocong Li","doi":"10.1109/COGINF.2010.5599802","DOIUrl":"https://doi.org/10.1109/COGINF.2010.5599802","url":null,"abstract":"A large number of noise data always exits when obtaining information through Internet, which deteriorates intrusion detection performance. In order to avoid the affection of noise data, data preprocessing needs to be done before the construction of hyperplane in Support Vector Machine (SVM). By importing fuzzy theory into SVM, a new method is proposed for cooperative network intrusion detection. Due to the various attack methods in different network protocol, a fuzzy membership function is formatted under each protocol, which means a unique Multi-Class SVM is suitable for only one network protocol. To implement this approach, a fuzzy Multi-Class-SVM-based cooperative network intrusion detection model with multi-agent architecture is presented in this paper, which is composed of three types of agents corresponding to TCP, UDP, and ICMP protocols, respectively and a statistic-based agent. Moreover, simulation experiments are performed by using KDD CUP 1999 data set while it is shown in the results that the training time can be significantly shortened, storage space requirement can be sharply reduced, and classification accuracy is improved apparently by using the SVM method preprocessing the data.","PeriodicalId":365083,"journal":{"name":"9th IEEE International Conference on Cognitive Informatics (ICCI'10)","volume":"41 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131054706","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}

{"title":"Using stochastic dynamic step length particle swarm optimization to direct orbits of chaotic systems","authors":"Xingjuan Cai, Z. Cui","doi":"10.1109/COGINF.2010.5599741","DOIUrl":"https://doi.org/10.1109/COGINF.2010.5599741","url":null,"abstract":"Stochastic dynamic step length particle swarm optimization (SDSLPSO) is a new novel variant of particle swarm optimization that incorporating the dynamic step length for each particle in each iteration. This strategy simulates the phenomenon that each bird adjusts its velocity automatically in the process to finding the prey. In this paper, SD-SLPSO is employed to solve the directing orbits of chaotic systems, simulation results show this new variant increases the performance significantly when compared with the standard version of particle swarm optimization.","PeriodicalId":365083,"journal":{"name":"9th IEEE International Conference on Cognitive Informatics (ICCI'10)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129355961","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}

{"title":"A study of particle swarm optimization for cognitive machines","authors":"Dario Schor, W. Kinsner","doi":"10.1109/COGINF.2010.5599684","DOIUrl":"https://doi.org/10.1109/COGINF.2010.5599684","url":null,"abstract":"This paper presents a study of the properties of optimization algorithms for use in cognitive machines through five key measures: (i) speed of convergence, (ii) degree of exploration of the parameter space, (iii) storage and system size, (iv) adaptability, and (v) multi-scale capabilities. Based on these factors, a novel study of the trajectories of a particle in the particle swarm optimization algorithm is performed both in the time and frequency domain. The analysis shows that the trajectories of particles can be separated into a transient and a steady state periods where the transient is wide-sense stationary with long term dependancies that show the evolutionary properties of the algorithm as it converges on a solution. The steady state shows an increased degree of exploration of the parameter space that allow the algorithm to improve on the solution found over time. The results show the advantages of particle swarm optimization and inherent properties that make this optimization algorithm a suitable choice for use in cognitive machines. The information learned from this analysis can further be used to extract complexity measures to classify the behavior and control of particle swarm optimization, and make proper quick decisions on what to do next. The decision process often requires more alternatives to be considered in a short window of time than it is physically possible for a real-time system [Kins04]. Thus, in order to make good decisions without exploring all possible paths, a cognitive system requires optimization techniques that can survey the possible options, and quickly select the best option possible. The paper reviews the requirements for an ideal optimization technique for use in cognitive systems and proposes the particle swarm optimization algorithm as one technique that is designed to satisfy these requirements. In order to show the properties of PSO, a novel trajectory, time, and frequency domain analyses of single particles along individual dimensions are presented.","PeriodicalId":365083,"journal":{"name":"9th IEEE International Conference on Cognitive Informatics (ICCI'10)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128044181","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}

{"title":"Comparing order entry subsequences related to CPOE correction factors","authors":"H. Abe, S. Tsumoto","doi":"10.1109/COGINF.2010.5599801","DOIUrl":"https://doi.org/10.1109/COGINF.2010.5599801","url":null,"abstract":"Computer physician order entry (CPOE) systems play an important role in hospital information systems to com-municate the orders from medical doctors to other medical staffs. However, there are still remaining order corrections and deletions, caused by both of changes of patients' condition and operational problems between a system and doctors. In this paper, we analyzed factors of medication order corrections for each patient by using order sequences a day. From the whole of the order entry sequences, we extracted characteristic order entry sub-sequences by using an automatic term extraction method in natural language processing. By constructing datasets consisting of the subsequences and the other patients' information, we obtained if-then rules. Then, we compare their accuracies of the if-then rule sets with/without the characteristic order entry subsequences for analyzing the order correction factors.","PeriodicalId":365083,"journal":{"name":"9th IEEE International Conference on Cognitive Informatics (ICCI'10)","volume":"34 7","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114035403","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}

{"title":"Cognitive computing and World Wide Wisdom (WWW+)","authors":"Yingxu Wang","doi":"10.1109/COGINF.2010.5599737","DOIUrl":"https://doi.org/10.1109/COGINF.2010.5599737","url":null,"abstract":"It is recognized that the key theoretical and technical problems toward the next generation internet are not only a speed issue, but also a more fundamental issue of the increasingly demands for the sharing of computational intelligent capabilities. According to cognitive informatics [1, 2, 3, 5, 9, 14, 16, 18], the cognitive information that humans acquire, process, retain, and share can be classified into four profound forms known as knowledge, experience, skill, and wisdom. Among them, wisdom is the most advanced cognitive objects, which is a form of natural intelligence of humans that transfers a query or instruction into an action or behavior based on a well developed reasoning and judgment. However, the current Internet is still remains as an information network. Towards the development of next generation Internet as a wisdom network, the World Wide Wisdom (WWW+) network infrastructures and technologies are yet to be sough t on the basis of cognitive informatics and cognitive computers. In WWW+, each node is a cognitive computer (CC) [3, 9, 10, 15], which is a form of autonomous and intelligent computers that think, perceive, and learn. CC enables the simulation of machinable thought such as computational inferences, reasoning, and causality analyses by autonomous inferences and perceptions mimicking the mechanisms of the brain [3, 15]. The cognitive learning engine of a CC is an autonomous learning system that enables machines learn in natural languages and symbolic notations. The cognitive search engine of a CC is a machine-learning-based search system that results in cognitive knowledge acquisitions and manipulations. On the basis of the development of CCs, the next generation internet, WWW+, will be developed as a world-wide intelligent network for knowledge processing, autonomous learning, and machine-supported problem solving. The theoretical foundations for WWW+ and cognitive computing are cognitive informatics [1, 2, 3, 5, 9, 14, 16, 18], with underpinning contemporary denotational mathematics [6, 12], such as concept algebra [7], system algebra [17], realtime process algebra [4, 8], granular algebra [12], and visual semantic algebra [11]. Denotational mathematics provides a coherent set of powerful mathematical means and explicit expressive power for the design, modeling, and implementation of cognitive computers and WWW+, as that of Boolean algebra for conventional computing technologies. WWW+ extends the current information-search-based Internet to wisdom providing and intelligence services that mimic and simulate the brain in the largest scope of the cyberspace in which each node plays a role as an autonomous super neural cell. As that the conventional Internet provides a solution to the “to be” category of problems for information sharing based on searching technologies, the WWW+-based internet solves the advanced “to do” category of problems for wisdom and intelligence capability sharing based on cognitive computing technologi","PeriodicalId":365083,"journal":{"name":"9th IEEE International Conference on Cognitive Informatics (ICCI'10)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114508279","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}

{"title":"Generic cabling with restrictions based on ant colony algorithm","authors":"Yunlong Wang, G. Luo","doi":"10.1109/COGINF.2010.5599817","DOIUrl":"https://doi.org/10.1109/COGINF.2010.5599817","url":null,"abstract":"Generic cabling is the key component and one of the basic foundations of intellig ent buildings. Acco rding to the analysis of the theory and o peration f low in generic cabling, generic cabling is a multiplex cable wiring problem and we have evolved the known conditions and the index constraints affecting generic cabling. A mathematical model was built based on ant the colony algorithm with multip le c onditions, and impr ovements were made on the or iginal basis to e xtend the ant c olony algorithm from the regular simple ant colony and structure to a multi-ant colon y an d s tructure. Th e eq uilibrium s ettlement of multiplex wiring was realized according to the introduction of the multi-ant colony model. Considering that the optimiz ation target should o ptimize the global wiring p ath, the ant cycle mod el was combined to extend the optimization target from the local wiring path to the entire wiring path, and to so lve the dra wbacks existing in the regular ant colony algorithm and other s earch algorithms that take the lo cal wiring path a s the optimiz ation target. Th e introduced r etrospective algo rithm make the ants avoid the path marked \"invalid \" in the subsequent sea rch process an d imp roves th e s earch p erformance an d convergence speed of th e ant colony algorithm. The results presented in this paper indicate that the improved ant colony algorithm efficiently handles th e ge neric cab ling i n in telligent b uildings acco rding to the results of the project data.","PeriodicalId":365083,"journal":{"name":"9th IEEE International Conference on Cognitive Informatics (ICCI'10)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126314270","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}

{"title":"Cognitive-driven requirements prioritization: A case study","authors":"Nadina Martinez Carod, A. Cechich","doi":"10.1109/COGINF.2010.5599774","DOIUrl":"https://doi.org/10.1109/COGINF.2010.5599774","url":null,"abstract":"Prioritizing software requirements includes negotiation among people involved in the process as well as an acceptance of the prioritization criteria. The analysis includes negotiation as an important issue, which becomes extremely difficult, as clients often do not know exactly what they need. To overcome this situation, aiming at improving stakeholder's negotiation, we propose reducing the gap of misunderstanding between them by the use of cognitive science. In this paper, we introduce a case study showing that cognitive profiles may affect requirement prioritization. A controlled experiment shows that elicitation techniques should be carefully selected according to cognitive skills to improve prioritization results.","PeriodicalId":365083,"journal":{"name":"9th IEEE International Conference on Cognitive Informatics (ICCI'10)","volume":"245 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130114955","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}

{"title":"Computers do better than experts matching faces in a large population","authors":"Liu Ding, C. Shu, Chi Fang, Xiaoqing Ding","doi":"10.1109/COGINF.2010.5599727","DOIUrl":"https://doi.org/10.1109/COGINF.2010.5599727","url":null,"abstract":"The performance of computer-based face recognition algorithms improves significantly recently. Although extensive evaluations of algorithms have been carried out, there has been little work on measuring the performance of experienced humans matching faces. We compared the face verification performance of 4504 experienced inspectors with a leading face recognition algorithm in a large population. Experts and algorithms determined whether face image pairs taken under real-world situation were pictures of the same person or not. The face recognition algorithm evidently surpassed experts on “easy” and “middle” face pairs, while on “hard” ones experts were superior to the algorithm. As a whole the algorithm outperformed experts on the face matching task. The distinct performance of the algorithm and experts on unfamiliar faces underscores the need to understand how much humans benefit from experience. It also suggested utilizing human-machine partnerships in security applications. A practical cascade system was proposed to reduce the workload of inspectors and achieve accuracy better than both experts and algorithms.","PeriodicalId":365083,"journal":{"name":"9th IEEE International Conference on Cognitive Informatics (ICCI'10)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127898542","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}

{"title":"Flight behavior recognizing in terminal area based on support vector machine","authors":"Laihong Hu, F. Sun, Huaping Liu, Hualong Xu","doi":"10.1109/COGINF.2010.5599761","DOIUrl":"https://doi.org/10.1109/COGINF.2010.5599761","url":null,"abstract":"The increasing demand for air travel is stressing the current Air Traffic Control (ATC). This is likely to cause both safety and performance degradation in the near future. In order to solve this problem, increasing the automation level of ATC is an important development direction. So flight behavior recognizing is becoming a key technique for ATC, for it is the basis of other function of ATC, such as landing scheduling, conflict detection, and so on. This paper introduced support vector machine (SVM) to solve flight behavior recognizing in terminal area, and designed multi-classification algorithm flow. The simulation results show that SVM is equal to this task.","PeriodicalId":365083,"journal":{"name":"9th IEEE International Conference on Cognitive Informatics (ICCI'10)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121275430","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}