this study investigates the augmentation of the crossoveronly G3-PCX evolutionary optimization algorithm with mutational diversity for solving multimodal global optimization problems. the objective is to empirically t...
详细信息
ISBN:
(纸本)9780889867307
this study investigates the augmentation of the crossoveronly G3-PCX evolutionary optimization algorithm with mutational diversity for solving multimodal global optimization problems. the objective is to empirically test and compare the optimization precision and dynamics of the two mutationally-augmented G3-PCX algorithms against the original G3-PCX algorithm based on a set of well-known test functions. Empirical tests on five benchmark continuous multimodal test functions have shown highly competitive performance in the augmented G3 algorithms which are called G3MD (G3 with Mutational Diversity) and G3SAM (G3 with Self- Adaptive Mutation) respectively where the proposed algorithms outperformed the standard G3 algorithm in terms of solution quality on two of the test problems. Analysis of the optimization dynamics reveals that the improved performance was due to the longer maintenance of genetic diversity through the mutational augmentation. Hence it is shown that the simple addition of Gaussian mutation can greatly enhance the optimization precision of RCGAs for solving large scale problems with highly deceptive fitness landscapes.
this paper presents a novel module placement based on genetic algorithm (GA) for macro-cell layouts placement that minimizes the chip area size. A binary tree method for non-slicing tree construction process is utiliz...
详细信息
ISBN:
(纸本)9780889867307
this paper presents a novel module placement based on genetic algorithm (GA) for macro-cell layouts placement that minimizes the chip area size. A binary tree method for non-slicing tree construction process is utilized for the placement and area optimization of macro-cell layouts in very large scale integrated (VLSI) design. the proposed algorithm have been developed using two types of GA: simple genetic algorithm (SGA) and adaptive genetic algorithm (AGA). the performance comparisons of these two techniques in achieving the optimal results are investigated and analyzed. the robustness of GA is also being examined in order to verify the GA performance stability. Based on the experimental results tested on Microelectronic Center of North Carolina (MCNC) benchmark circuit's data set, it exhibits that both algorithms acquire acceptable performance quality to the slicing floorplan approach. AGA performs better than SGA as it converges faster to the optimal result and obtains better optimum area. However, SGA appears to be more robust than AGA.
In this paper we introduce an update of our work about developing a distance learning environment based on a collaborative bookmark management system. We introduce EasyInfo, an hybrid recommender architecture extensio...
详细信息
ISBN:
(纸本)9780889866997
In this paper we introduce an update of our work about developing a distance learning environment based on a collaborative bookmark management system. We introduce EasyInfo, an hybrid recommender architecture extension, which processes resources in order to extract concepts using semantic capabilities. thanks to its resource sharing and recommendation facilities, the system contributes to human collaborative activities: it supports group collaboration among people involved in a task, independently from time and space distance, and learns from positive and negative experiences in group practice.
this paper presents the use of coefficients derived from linear predictive coding (LPC) based on the dynamic time warping (DTW). the derived coefficients are called the DTW frame-fixing coefficients (DTW-FF), they are...
详细信息
ISBN:
(纸本)9780889867307
this paper presents the use of coefficients derived from linear predictive coding (LPC) based on the dynamic time warping (DTW). the derived coefficients are called the DTW frame-fixing coefficients (DTW-FF), they are used as input to the back-propagation neural network for speech pattern recognition. this paper also presents the study of pitch as a contributing input feature added to the DTW-FF coefficients. the results showed a good performance and improvement as high as 100% when using pitch along with DTW-FF feature. It is known that back-propagation NN is capable of handling large learning problems and is a very promising method due to its ability to train data and classify them. Current method of back- propagation is using steepest gradient descent whereby this method is exposed to bad local-minima. In this study, the network is designed to handle the parallel processing of multiplesamples/words, therefore it caused the network to compute a large amount of connection weights and error updates at a time, therefore longer time is taken for network convergence to its global minima. Since the Conjugate Gradient method has been proven of being able to accelerate the network convergence, it is applied into the back-propagation mechanism to replace the steepest gradient descent algorithm. the outcome showed that the convergence rate was improved when conjugate gradient method is used in the back-propagation algorithm.
Aspect-oriented programming is a new paradigm that complements the object-oriented technology. the premise of aspect-oriented technology is the separation of concerns. Certain system properties tend to cut across grou...
详细信息
ISBN:
(纸本)9780889867307
Aspect-oriented programming is a new paradigm that complements the object-oriented technology. the premise of aspect-oriented technology is the separation of concerns. Certain system properties tend to cut across group of functional components such as concurrency, security, and fault tolerance are examples of these crosscutting concerns. Aspect orientation attempts to modularize these crosscutting properties in order to avoid the code-tangling phenomena. Objects are independent entities that cooperate together t0achieve a certain task, how can we mange object interaction without violating basic object orientation principles like abstraction, what triggers an object to perform its functionality, what constraints that an object must consider before performing its task(s) are, how an object behavior impacts other object(s) behavior, how we can model our aspect oriented system with all the above questions in mind using existing CASE tools and guarantee separation of concerns at the implementation (automatic code generation). In this position paper presents a formal methodology that addresses the above questions and supports separation of concerns for system software. the paper demonstrates aspect-oriented framework applying at the design and implementation phase with separation of system properties. Our approach uses CASE tools supporting UML without any extensions to it. Rhapsody CASE tool has been used to model and automatically generate code since it supports UML diagrams which enable us to present different views usig different UML diagrams (OMD, SD, Statecharts, and Use Case diagrams).
In today's world, the use of parallel programming and architectures is essential for simulating practical problems in engineering and related disciplines. Remarkable progress in CPU architecture (multi- and manyco...
详细信息
advances in rehabilitation and assistive technologies can be seen today. Nevertheless, there still remains an area that ought to be examined more seriously from an economic standpoint. We call this area a mechatronics...
详细信息
ISBN:
(纸本)9780889867406
advances in rehabilitation and assistive technologies can be seen today. Nevertheless, there still remains an area that ought to be examined more seriously from an economic standpoint. We call this area a mechatronics support service, which lies as a support technology centered on mechanics, electronics, and computing. this paper explores key issues in the establishment of a mechatronics service framework that hosts micro and macro control for the smooth navigation of mobile wheelchairs and surrounding information systems. Specifically, we propose a systems architecture that facilitates terrain surveillance and intelligence gathering through laser sensor implanted in the wheelchair, for the purpose to identify unusual patterns of movement to predict accidents. We also emphasize the importance of information technology which is a key for providing flexible transportation services for those in need of wheelchairs. the significance of this research for the longer-term goals lies in its implications for adaptation of our intelligent model into the future welfare activities. Foundations for and mechatronics specifications for micro and macro-control architecture are presented.
Transposing handwriting through a digital pen into typed text for language learning are discussed. Researchers agree that there are specificities of first language (L1) writing that could affect writing in a second la...
详细信息
ISBN:
(纸本)9780889866997
Transposing handwriting through a digital pen into typed text for language learning are discussed. Researchers agree that there are specificities of first language (L1) writing that could affect writing in a second language (L2) because writing styles are language specific. In our study of the conversion of handwritten notes to computer printed text withthe Logitech [1] MyScripts handwriting recognition software in both French and English, we uncovered what affected the conversion to typed texts of the writing modes in L1 and L2 by the same writer. the question of penmanship is explored as is the question of transfer from handwritten language to the printed conversion. Suggestions are made about possible adjustments, both to the technology and for the user in the passage from L1 to L2.
Mobile e-Learning is based on the combination of mobile data communication technology and wireless Internet. It is important to study and analyze mobile e-Learning research of domestic and foreign, because it will dri...
详细信息
ISBN:
(纸本)9783540850328
Mobile e-Learning is based on the combination of mobile data communication technology and wireless Internet. It is important to study and analyze mobile e-Learning research of domestic and foreign, because it will drive the future education and learning markets. this paper summarizes the research on Mobile e-Learning around the whole world and shows clearly construction directions needed toward in China. A systematic discussion and analysis of e-learning providers, educational institutions, and their cooperation is also presented.
暂无评论