The volume includes a set of selected papers extended and revised from the 2011 International Conference on Mechanical Engineering and Technology, held on London, UK, November 24-25, 2011. Mechanical engineering techn...
ISBN:
(数字)9783642273346
ISBN:
(纸本)3642273335
The volume includes a set of selected papers extended and revised from the 2011 International Conference on Mechanical Engineering and Technology, held on London, UK, November 24-25, 2011. Mechanical engineering technology is the application of physical principles and current technological developments to the creation of useful machinery and operation design. Technologies such as solid models may be used as the basis for finite element analysis (FEA) and / or computational fluid dynamics (CFD) of the design. Through the application of computer-aided manufacturing (CAM), the models may also be used directly by software to create "instructions" for the manufacture of objects represented by the models, through computer numerically controlled (CNC) machining or other automated processes, without the need for intermediate drawings. This volume covers the subject areas of mechanical engineering and technology, and also covers interdisciplinary subject areas of computers, communications, control and automation. We hope that researchers, graduate students and other interested readers benefit scientifically from the book and also find it stimulating in the process.
Ambient Intelligence (AmI) is a recent paradigm emerging from Artificial Intelligence (AI), where computers are used as proactive tools assisting people with their day-to-day activities, making everyones life more com...
ISBN:
(数字)9783642287831
ISBN:
(纸本)3642287824
Ambient Intelligence (AmI) is a recent paradigm emerging from Artificial Intelligence (AI), where computers are used as proactive tools assisting people with their day-to-day activities, making everyones life more comfortable. Another main concern of AmI originates from the human computer interaction domain and focuses on offering ways to interact with systems in a more natural way by means user friendly interfaces. This field is evolving quickly as can be witnessed by the emerging natural language and gesture based types of interaction. The inclusion of computational power and communication technologies in everyday objects is growing and their embedding into our environments should be as invisible as possible. In order for AmI to be successful, human interaction with computing power and embedded systems in the surroundings should be smooth and happen without people actually noticing it. The only awareness people should have arises from AmI: more safety, comfort and wellbeing, emerging in a natural and inherent way. ISAmI is the International Symposium on Ambient Intelligence, aiming to bring together researchers from various disciplines that constitute the scientific field of Ambient Intelligence to present and discuss the latest results, new ideas, projects and lessons learned.
We consider a classification process, that the representation precision of new examples is interactively increased. We use an attribute value ontology (AVO) to represent examples at different levels of abstraction (le...
详细信息
ISBN:
(纸本)9783319023090
We consider a classification process, that the representation precision of new examples is interactively increased. We use an attribute value ontology (AVO) to represent examples at different levels of abstraction (levels of precision). This precision can be improved by conducting diagnostic tests. The selection of these diagnostic tests is generally a non-trivial task. We consider the hypothesis-driven interactive classification, where a decision maker chooses diagnostic tests that approve or reject her hypothesis (the classification of a new example to a one or more selected decision classes). Specifically, we present two approaches to the selection of diagnostic tests: the use of the measure of information gain and the analysis of the classification results for these diagnostic tests using an ontological Bayes classifier (OBC).
Automated recognition of complex video events poses challenges related to: selection of formalisms for efficient event modeling and analysis, mapping semantic high-level concepts used in specifications on information ...
详细信息
ISBN:
(纸本)9783319023090
Automated recognition of complex video events poses challenges related to: selection of formalisms for efficient event modeling and analysis, mapping semantic high-level concepts used in specifications on information extracted from video sequences, as well as managing uncertainty associated with this information. We propose Fuzzy Semantic Petri Nets (FSPN) as a tool aimed at solving the mentioned problems. FSPN are Petri nets coupled with an underlying fuzzy ontology. The ontology stores assertions (facts) concerning object classification and detected relations. Fuzzy predicates querying the ontology are used as transition guards. Places in FSPN represent scenario steps. Tokens carry information on objects participating in a scenario and have weights expressing likelihood of a step occurrence. FSPN enable detection of events occurring concurrently, analysis of various combinations of objects and reasoning about alternatives.
This work introduces a new fuzzy c-regression models with various loss functions. The algorithm consists in solving a sequence of weighted quadratic minimization problems where the weights used for the next iteration ...
详细信息
ISBN:
(纸本)9783319023090
This work introduces a new fuzzy c-regression models with various loss functions. The algorithm consists in solving a sequence of weighted quadratic minimization problems where the weights used for the next iteration depend on values of models residuals for the current iteration. Simulations on real-life ECG signals are realized to evaluate the performance of the fuzzy clustering method.
Support vector machines (SVM) and neuro-fuzzy systems (NFS) are efficient tools for regression tasks. The problem of the SVMs is the proper choice of kernel functions. Our idea is to transform the task's domain wi...
详细信息
ISBN:
(纸本)9783319023090
Support vector machines (SVM) and neuro-fuzzy systems (NFS) are efficient tools for regression tasks. The problem of the SVMs is the proper choice of kernel functions. Our idea is to transform the task's domain with NFS so that linear kernel can be applied. The paper is accompanied by numerical experiments.
The last two decades increased the insistence to ensure security of strategic objects such as military bases, airports, fuel plants and others. Effective protection is only possible using systems utilizing latest tech...
详细信息
ISBN:
(纸本)9783319023090
The last two decades increased the insistence to ensure security of strategic objects such as military bases, airports, fuel plants and others. Effective protection is only possible using systems utilizing latest technology. This paper presents characteristic of modern security systems, and describes SMAC system developed at Silesian University of Technology. It is based on microwave radars supported by mobile devices (UAI) equipped with GPS receivers transmitting current position using a radio channel to recognize objects as authorized to stay in the restricted area. As GPS accuracy is worse than radar resolution so research has been done to ensure proper detection. This paper also presents the discussion of the influence of radar resolution on object recognition.
In the paper the conditional fuzzy clustering algorithm dedicated to classification methods is proposed. Three methods determining conditional variable values are presented. The clustering is applied to the nonlinear ...
详细信息
ISBN:
(纸本)9783319023090
In the paper the conditional fuzzy clustering algorithm dedicated to classification methods is proposed. Three methods determining conditional variable values are presented. The clustering is applied to the nonlinear extension of the IRLS classifier, which uses different loss functions. Classification quality and computing time achieved for six benchmark datasets are compared with the Lagrangian SVM method.
暂无评论